diff options
170 files changed, 3503 insertions, 1879 deletions
diff --git a/Documentation/ABI/testing/sysfs-class-cxl b/Documentation/ABI/testing/sysfs-class-cxl index 640f65e79ef1..267920a1874b 100644 --- a/Documentation/ABI/testing/sysfs-class-cxl +++ b/Documentation/ABI/testing/sysfs-class-cxl @@ -69,7 +69,9 @@ Date: September 2014 Contact: linuxppc-dev@lists.ozlabs.org Description: read/write Set the mode for prefaulting in segments into the segment table - when performing the START_WORK ioctl. Possible values: + when performing the START_WORK ioctl. Only applicable when + running under hashed page table mmu. + Possible values: none: No prefaulting (default) work_element_descriptor: Treat the work element descriptor as an effective address and diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index c32a181a7cbb..23247fa551e7 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -162,6 +162,7 @@ config PPC select BUILDTIME_EXTABLE_SORT select CLONE_BACKWARDS select DCACHE_WORD_ACCESS if PPC64 && CPU_LITTLE_ENDIAN + select DYNAMIC_FTRACE if FUNCTION_TRACER select EDAC_ATOMIC_SCRUB select EDAC_SUPPORT select GENERIC_ATOMIC64 if PPC32 @@ -220,6 +221,7 @@ config PPC select HAVE_PERF_USER_STACK_DUMP select HAVE_RCU_TABLE_FREE if SMP select HAVE_REGS_AND_STACK_ACCESS_API + select HAVE_RELIABLE_STACKTRACE if PPC64 && CPU_LITTLE_ENDIAN select HAVE_SYSCALL_TRACEPOINTS select HAVE_VIRT_CPU_ACCOUNTING select HAVE_IRQ_TIME_ACCOUNTING diff --git a/arch/powerpc/boot/dts/fsl/t104xqds.dtsi b/arch/powerpc/boot/dts/fsl/t104xqds.dtsi index 2fd4cbe7098f..615479732252 100644 --- a/arch/powerpc/boot/dts/fsl/t104xqds.dtsi +++ b/arch/powerpc/boot/dts/fsl/t104xqds.dtsi @@ -269,7 +269,7 @@ i2c@118000 { pca9547@77 { - compatible = "philips,pca9547"; + compatible = "nxp,pca9547"; reg = <0x77>; }; rtc@68 { diff --git a/arch/powerpc/boot/dts/sbc8349.dts b/arch/powerpc/boot/dts/sbc8349.dts deleted file mode 100644 index fc89e00b765c..000000000000 --- a/arch/powerpc/boot/dts/sbc8349.dts +++ /dev/null @@ -1,331 +0,0 @@ -/* - * SBC8349E Device Tree Source - * - * Copyright 2007 Wind River Inc. - * - * Paul Gortmaker (see MAINTAINERS for contact information) - * - * -based largely on the Freescale MPC834x_MDS dts. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - */ - -/dts-v1/; - -/ { - model = "SBC8349E"; - compatible = "SBC834xE"; - #address-cells = <1>; - #size-cells = <1>; - - aliases { - ethernet0 = &enet0; - ethernet1 = &enet1; - serial0 = &serial0; - serial1 = &serial1; - pci0 = &pci0; - }; - - cpus { - #address-cells = <1>; - #size-cells = <0>; - - PowerPC,8349@0 { - device_type = "cpu"; - reg = <0x0>; - d-cache-line-size = <32>; - i-cache-line-size = <32>; - d-cache-size = <32768>; - i-cache-size = <32768>; - timebase-frequency = <0>; // from bootloader - bus-frequency = <0>; // from bootloader - clock-frequency = <0>; // from bootloader - }; - }; - - memory { - device_type = "memory"; - reg = <0x00000000 0x10000000>; // 256MB at 0 - }; - - soc8349@e0000000 { - #address-cells = <1>; - #size-cells = <1>; - device_type = "soc"; - ranges = <0x0 0xe0000000 0x00100000>; - reg = <0xe0000000 0x00000200>; - bus-frequency = <0>; - - wdt@200 { - compatible = "mpc83xx_wdt"; - reg = <0x200 0x100>; - }; - - i2c@3000 { - #address-cells = <1>; - #size-cells = <0>; - cell-index = <0>; - compatible = "fsl-i2c"; - reg = <0x3000 0x100>; - interrupts = <14 0x8>; - interrupt-parent = <&ipic>; - dfsrr; - }; - - i2c@3100 { - #address-cells = <1>; - #size-cells = <0>; - cell-index = <1>; - compatible = "fsl-i2c"; - reg = <0x3100 0x100>; - interrupts = <15 0x8>; - interrupt-parent = <&ipic>; - dfsrr; - }; - - spi@7000 { - cell-index = <0>; - compatible = "fsl,spi"; - reg = <0x7000 0x1000>; - interrupts = <16 0x8>; - interrupt-parent = <&ipic>; - mode = "cpu"; - }; - - dma@82a8 { - #address-cells = <1>; - #size-cells = <1>; - compatible = "fsl,mpc8349-dma", "fsl,elo-dma"; - reg = <0x82a8 4>; - ranges = <0 0x8100 0x1a8>; - interrupt-parent = <&ipic>; - interrupts = <71 8>; - cell-index = <0>; - dma-channel@0 { - compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel"; - reg = <0 0x80>; - cell-index = <0>; - interrupt-parent = <&ipic>; - interrupts = <71 8>; - }; - dma-channel@80 { - compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel"; - reg = <0x80 0x80>; - cell-index = <1>; - interrupt-parent = <&ipic>; - interrupts = <71 8>; - }; - dma-channel@100 { - compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel"; - reg = <0x100 0x80>; - cell-index = <2>; - interrupt-parent = <&ipic>; - interrupts = <71 8>; - }; - dma-channel@180 { - compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel"; - reg = <0x180 0x28>; - cell-index = <3>; - interrupt-parent = <&ipic>; - interrupts = <71 8>; - }; - }; - - /* phy type (ULPI or SERIAL) are only types supported for MPH */ - /* port = 0 or 1 */ - usb@22000 { - compatible = "fsl-usb2-mph"; - reg = <0x22000 0x1000>; - #address-cells = <1>; - #size-cells = <0>; - interrupt-parent = <&ipic>; - interrupts = <39 0x8>; - phy_type = "ulpi"; - port0; - }; - - enet0: ethernet@24000 { - #address-cells = <1>; - #size-cells = <1>; - cell-index = <0>; - device_type = "network"; - model = "TSEC"; - compatible = "gianfar"; - reg = <0x24000 0x1000>; - ranges = <0x0 0x24000 0x1000>; - local-mac-address = [ 00 00 00 00 00 00 ]; - interrupts = <32 0x8 33 0x8 34 0x8>; - interrupt-parent = <&ipic>; - tbi-handle = <&tbi0>; - phy-handle = <&phy0>; - linux,network-index = <0>; - - mdio@520 { - #address-cells = <1>; - #size-cells = <0>; - compatible = "fsl,gianfar-mdio"; - reg = <0x520 0x20>; - - phy0: ethernet-phy@19 { - interrupt-parent = <&ipic>; - interrupts = <20 0x8>; - reg = <0x19>; - }; - - phy1: ethernet-phy@1a { - interrupt-parent = <&ipic>; - interrupts = <21 0x8>; - reg = <0x1a>; - }; - - tbi0: tbi-phy@11 { - reg = <0x11>; - device_type = "tbi-phy"; - }; - }; - }; - - enet1: ethernet@25000 { - #address-cells = <1>; - #size-cells = <1>; - cell-index = <1>; - device_type = "network"; - model = "TSEC"; - compatible = "gianfar"; - reg = <0x25000 0x1000>; - ranges = <0x0 0x25000 0x1000>; - local-mac-address = [ 00 00 00 00 00 00 ]; - interrupts = <35 0x8 36 0x8 37 0x8>; - interrupt-parent = <&ipic>; - tbi-handle = <&tbi1>; - phy-handle = <&phy1>; - linux,network-index = <1>; - - mdio@520 { - #address-cells = <1>; - #size-cells = <0>; - compatible = "fsl,gianfar-tbi"; - reg = <0x520 0x20>; - - tbi1: tbi-phy@11 { - reg = <0x11>; - device_type = "tbi-phy"; - }; - }; - }; - - serial0: serial@4500 { - cell-index = <0>; - device_type = "serial"; - compatible = "fsl,ns16550", "ns16550"; - reg = <0x4500 0x100>; - clock-frequency = <0>; - interrupts = <9 0x8>; - interrupt-parent = <&ipic>; - }; - - serial1: serial@4600 { - cell-index = <1>; - device_type = "serial"; - compatible = "fsl,ns16550", "ns16550"; - reg = <0x4600 0x100>; - clock-frequency = <0>; - interrupts = <10 0x8>; - interrupt-parent = <&ipic>; - }; - - crypto@30000 { - compatible = "fsl,sec2.0"; - reg = <0x30000 0x10000>; - interrupts = <11 0x8>; - interrupt-parent = <&ipic>; - fsl,num-channels = <4>; - fsl,channel-fifo-len = <24>; - fsl,exec-units-mask = <0x7e>; - fsl,descriptor-types-mask = <0x01010ebf>; - }; - - /* IPIC - * interrupts cell = <intr #, sense> - * sense values match linux IORESOURCE_IRQ_* defines: - * sense == 8: Level, low assertion - * sense == 2: Edge, high-to-low change - */ - ipic: pic@700 { - interrupt-controller; - #address-cells = <0>; - #interrupt-cells = <2>; - reg = <0x700 0x100>; - device_type = "ipic"; - }; - }; - - localbus@e0005000 { - #address-cells = <2>; - #size-cells = <1>; - compatible = "fsl,mpc8349-localbus", "simple-bus"; - reg = <0xe0005000 0x1000>; - interrupts = <77 0x8>; - interrupt-parent = <&ipic>; - ranges = <0x0 0x0 0xff800000 0x00800000 /* 8MB Flash */ - 0x1 0x0 0xf8000000 0x00002000 /* 8KB EEPROM */ - 0x2 0x0 0x10000000 0x04000000 /* 64MB SDRAM */ - 0x3 0x0 0x10000000 0x04000000>; /* 64MB SDRAM */ - - flash@0,0 { - #address-cells = <1>; - #size-cells = <1>; - compatible = "intel,28F640J3A", "cfi-flash"; - reg = <0x0 0x0 0x800000>; - bank-width = <2>; - device-width = <1>; - - partition@0 { - label = "u-boot"; - reg = <0x00000000 0x00040000>; - read-only; - }; - - partition@40000 { - label = "user"; - reg = <0x00040000 0x006c0000>; - }; - - partition@700000 { - label = "legacy u-boot"; - reg = <0x00700000 0x00100000>; - read-only; - }; - - }; - }; - - pci0: pci@e0008500 { - interrupt-map-mask = <0xf800 0x0 0x0 0x7>; - interrupt-map = < - - /* IDSEL 0x11 */ - 0x8800 0x0 0x0 0x1 &ipic 48 0x8 - 0x8800 0x0 0x0 0x2 &ipic 17 0x8 - 0x8800 0x0 0x0 0x3 &ipic 18 0x8 - 0x8800 0x0 0x0 0x4 &ipic 19 0x8>; - - interrupt-parent = <&ipic>; - interrupts = <0x42 0x8>; - bus-range = <0 0>; - ranges = <0x02000000 0x0 0x90000000 0x90000000 0x0 0x10000000 - 0x42000000 0x0 0x80000000 0x80000000 0x0 0x10000000 - 0x01000000 0x0 0x00000000 0xe2000000 0x0 0x00100000>; - clock-frequency = <66666666>; - #interrupt-cells = <1>; - #size-cells = <2>; - #address-cells = <3>; - reg = <0xe0008500 0x100 /* internal registers */ - 0xe0008300 0x8>; /* config space access registers */ - compatible = "fsl,mpc8349-pci"; - device_type = "pci"; - }; -}; diff --git a/arch/powerpc/configs/83xx/sbc834x_defconfig b/arch/powerpc/configs/83xx/sbc834x_defconfig deleted file mode 100644 index 7d74699334da..000000000000 --- a/arch/powerpc/configs/83xx/sbc834x_defconfig +++ /dev/null @@ -1,74 +0,0 @@ -CONFIG_SYSVIPC=y -CONFIG_LOG_BUF_SHIFT=14 -CONFIG_BLK_DEV_INITRD=y -CONFIG_EXPERT=y -# CONFIG_KALLSYMS is not set -CONFIG_SLAB=y -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -# CONFIG_BLK_DEV_BSG is not set -# CONFIG_PPC_CHRP is not set -# CONFIG_PPC_PMAC is not set -CONFIG_PPC_83xx=y -CONFIG_SBC834x=y -CONFIG_GEN_RTC=y -CONFIG_PCI=y -CONFIG_NET=y -CONFIG_PACKET=y -CONFIG_UNIX=y -CONFIG_XFRM_USER=m -CONFIG_INET=y -CONFIG_IP_MULTICAST=y -CONFIG_IP_PNP=y -CONFIG_IP_PNP_DHCP=y -CONFIG_IP_PNP_BOOTP=y -CONFIG_SYN_COOKIES=y -# CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" -# CONFIG_FW_LOADER is not set -CONFIG_MTD=y -CONFIG_MTD_CMDLINE_PARTS=y -CONFIG_MTD_BLOCK=y -CONFIG_MTD_CFI=y -CONFIG_MTD_CFI_INTELEXT=y -CONFIG_MTD_PHYSMAP_OF=y -CONFIG_BLK_DEV_LOOP=y -CONFIG_BLK_DEV_RAM=y -CONFIG_BLK_DEV_RAM_SIZE=32768 -CONFIG_SCSI=y -# CONFIG_SCSI_PROC_FS is not set -CONFIG_BLK_DEV_SD=y -# CONFIG_SCSI_LOWLEVEL is not set -CONFIG_NETDEVICES=y -CONFIG_GIANFAR=y -CONFIG_BROADCOM_PHY=y -# CONFIG_INPUT_KEYBOARD is not set -# CONFIG_INPUT_MOUSE is not set -# CONFIG_SERIO is not set -# CONFIG_VT is not set -CONFIG_SERIAL_8250=y -CONFIG_SERIAL_8250_CONSOLE=y -# CONFIG_SERIAL_8250_PCI is not set -CONFIG_SERIAL_8250_NR_UARTS=2 -CONFIG_SERIAL_8250_RUNTIME_UARTS=2 -# CONFIG_HW_RANDOM is not set -CONFIG_I2C=y -CONFIG_I2C_CHARDEV=y -CONFIG_I2C_MPC=y -CONFIG_WATCHDOG=y -# CONFIG_USB_HID is not set -CONFIG_USB=y -CONFIG_USB_MON=y -CONFIG_USB_EHCI_HCD=y -CONFIG_USB_EHCI_FSL=y -CONFIG_USB_STORAGE=y -CONFIG_EXT2_FS=y -CONFIG_EXT4_FS=y -CONFIG_PROC_KCORE=y -CONFIG_TMPFS=y -CONFIG_NFS_FS=y -CONFIG_NFS_V4=y -CONFIG_ROOT_NFS=y -CONFIG_CRYPTO_ECB=m -CONFIG_CRYPTO_PCBC=m -# CONFIG_CRYPTO_HW is not set diff --git a/arch/powerpc/configs/powernv_defconfig b/arch/powerpc/configs/powernv_defconfig index 9e92aa6a52ba..6ab34e60495f 100644 --- a/arch/powerpc/configs/powernv_defconfig +++ b/arch/powerpc/configs/powernv_defconfig @@ -38,7 +38,9 @@ CONFIG_MODULE_UNLOAD=y CONFIG_MODVERSIONS=y CONFIG_MODULE_SRCVERSION_ALL=y CONFIG_PARTITION_ADVANCED=y +CONFIG_SCOM_DEBUGFS=y CONFIG_OPAL_PRD=y +CONFIG_PPC_MEMTRACE=y # CONFIG_PPC_PSERIES is not set # CONFIG_PPC_OF_BOOT_TRAMPOLINE is not set CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y @@ -54,7 +56,10 @@ CONFIG_NUMA=y CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y +CONFIG_MEMORY_FAILURE=y +CONFIG_HWPOISON_INJECT=m CONFIG_TRANSPARENT_HUGEPAGE=y +CONFIG_DEFERRED_STRUCT_PAGE_INIT=y CONFIG_PPC_64K_PAGES=y CONFIG_PPC_SUBPAGE_PROT=y CONFIG_SCHED_SMT=y @@ -72,7 +77,13 @@ CONFIG_SYN_COOKIES=y CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m -# CONFIG_IPV6 is not set +CONFIG_INET6_AH=m +CONFIG_INET6_ESP=m +CONFIG_INET6_IPCOMP=m +CONFIG_INET6_XFRM_MODE_TRANSPORT=m +CONFIG_INET6_XFRM_MODE_TUNNEL=m +CONFIG_INET6_XFRM_MODE_BEET=m +CONFIG_IPV6_SIT=m CONFIG_NETFILTER=y # CONFIG_NETFILTER_ADVANCED is not set CONFIG_BRIDGE=m @@ -81,33 +92,28 @@ CONFIG_NET_SCHED=y CONFIG_NET_CLS_BPF=m CONFIG_NET_CLS_ACT=y CONFIG_NET_ACT_BPF=m +CONFIG_DNS_RESOLVER=y CONFIG_BPF_JIT=y +# CONFIG_WIRELESS is not set CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y CONFIG_MTD=y CONFIG_MTD_BLOCK=y CONFIG_MTD_POWERNV_FLASH=y -CONFIG_PARPORT=m -CONFIG_PARPORT_PC=m -CONFIG_BLK_DEV_FD=m CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_NBD=m -CONFIG_BLK_DEV_RAM=y +CONFIG_BLK_DEV_RAM=m CONFIG_BLK_DEV_RAM_SIZE=65536 -CONFIG_VIRTIO_BLK=m CONFIG_BLK_DEV_NVME=y -CONFIG_IDE=y -CONFIG_BLK_DEV_IDECD=y -CONFIG_BLK_DEV_GENERIC=y -CONFIG_BLK_DEV_AMD74XX=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m -CONFIG_BLK_DEV_SR=y +CONFIG_BLK_DEV_SR=m CONFIG_BLK_DEV_SR_VENDOR=y -CONFIG_CHR_DEV_SG=y +CONFIG_CHR_DEV_SG=m CONFIG_SCSI_CONSTANTS=y -CONFIG_SCSI_FC_ATTRS=y +CONFIG_SCSI_SCAN_ASYNC=y +CONFIG_SCSI_FC_ATTRS=m CONFIG_SCSI_SRP_ATTRS=y CONFIG_SCSI_CXGB3_ISCSI=m CONFIG_SCSI_CXGB4_ISCSI=m @@ -121,7 +127,6 @@ CONFIG_SCSI_IPR=y CONFIG_SCSI_QLA_FC=m CONFIG_SCSI_QLA_ISCSI=m CONFIG_SCSI_LPFC=m -CONFIG_SCSI_VIRTIO=m CONFIG_SCSI_DH=y CONFIG_SCSI_DH_RDAC=m CONFIG_SCSI_DH_ALUA=m @@ -152,16 +157,16 @@ CONFIG_DUMMY=m CONFIG_MACVLAN=m CONFIG_MACVTAP=m CONFIG_VXLAN=m -CONFIG_NETCONSOLE=y +CONFIG_NETCONSOLE=m CONFIG_TUN=m CONFIG_VETH=m -CONFIG_VIRTIO_NET=m CONFIG_VORTEX=m CONFIG_ACENIC=m CONFIG_ACENIC_OMIT_TIGON_I=y CONFIG_PCNET32=m CONFIG_TIGON3=y CONFIG_BNX2X=m +# CONFIG_CAVIUM_PTP is not set CONFIG_CHELSIO_T1=m CONFIG_BE2NET=m CONFIG_S2IO=m @@ -172,46 +177,62 @@ CONFIG_IXGB=m CONFIG_IXGBE=m CONFIG_I40E=m CONFIG_MLX4_EN=m +CONFIG_MLX5_CORE=m +CONFIG_MLX5_FPGA=y +CONFIG_MLX5_CORE_EN=y +CONFIG_MLX5_CORE_IPOIB=y CONFIG_MYRI10GE=m CONFIG_QLGE=m CONFIG_NETXEN_NIC=m -CONFIG_PPP=m -CONFIG_PPP_BSDCOMP=m -CONFIG_PPP_DEFLATE=m -CONFIG_PPPOE=m -CONFIG_PPP_ASYNC=m -CONFIG_PPP_SYNC_TTY=m +CONFIG_USB_NET_DRIVERS=m +# CONFIG_WLAN is not set CONFIG_INPUT_EVDEV=m -CONFIG_INPUT_MISC=y -# CONFIG_SERIO_SERPORT is not set +# CONFIG_INPUT_KEYBOARD is not set +# CONFIG_INPUT_MOUSE is not set +# CONFIG_SERIO is not set +# CONFIG_LEGACY_PTYS is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_8250_PCI=m CONFIG_SERIAL_JSM=m -CONFIG_VIRTIO_CONSOLE=m CONFIG_IPMI_HANDLER=y CONFIG_IPMI_DEVICE_INTERFACE=y CONFIG_IPMI_POWERNV=y -CONFIG_RAW_DRIVER=y -CONFIG_MAX_RAW_DEVS=1024 +# CONFIG_DEVPORT is not set CONFIG_I2C_CHARDEV=y +# CONFIG_PTP_1588_CLOCK is not set CONFIG_DRM=y CONFIG_DRM_AST=y CONFIG_FIRMWARE_EDID=y CONFIG_FB_OF=y -CONFIG_FB_MATROX=y +CONFIG_FB_MATROX=m CONFIG_FB_MATROX_MILLENIUM=y CONFIG_FB_MATROX_MYSTIQUE=y CONFIG_FB_MATROX_G=y -CONFIG_FB_RADEON=y -CONFIG_FB_IBM_GXT4500=y +CONFIG_FB_RADEON=m +CONFIG_FB_IBM_GXT4500=m CONFIG_LCD_PLATFORM=m +CONFIG_BACKLIGHT_GENERIC=m # CONFIG_VGA_CONSOLE is not set CONFIG_LOGO=y -CONFIG_HID_GYRATION=y -CONFIG_HID_PANTHERLORD=y -CONFIG_HID_PETALYNX=y -CONFIG_HID_SAMSUNG=y -CONFIG_HID_SUNPLUS=y +CONFIG_HID_A4TECH=m +CONFIG_HID_APPLE=m +CONFIG_HID_BELKIN=m +CONFIG_HID_CHERRY=m +CONFIG_HID_CHICONY=m +CONFIG_HID_CYPRESS=m +CONFIG_HID_EZKEY=m +CONFIG_HID_GYRATION=m +CONFIG_HID_ITE=m +CONFIG_HID_KENSINGTON=m +CONFIG_HID_LOGITECH=m +CONFIG_HID_MICROSOFT=m +CONFIG_HID_MONTEREY=m +CONFIG_HID_PANTHERLORD=m +CONFIG_HID_PETALYNX=m +CONFIG_HID_SAMSUNG=m +CONFIG_HID_SUNPLUS=m +CONFIG_USB_HID=m CONFIG_USB_HIDDEV=y CONFIG_USB=y CONFIG_USB_MON=m @@ -219,6 +240,7 @@ CONFIG_USB_XHCI_HCD=y CONFIG_USB_EHCI_HCD=y # CONFIG_USB_EHCI_HCD_PPC_OF is not set CONFIG_USB_OHCI_HCD=y +CONFIG_USB_OHCI_HCD_PCI=m CONFIG_USB_STORAGE=y CONFIG_NEW_LEDS=y CONFIG_LEDS_CLASS=m @@ -236,8 +258,9 @@ CONFIG_INFINIBAND_SRP=m CONFIG_INFINIBAND_ISER=m CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_GENERIC=y -CONFIG_VIRTIO_PCI=m -CONFIG_VIRTIO_BALLOON=m +# CONFIG_VIRTIO_MENU is not set +CONFIG_LIBNVDIMM=y +# CONFIG_ND_BLK is not set CONFIG_EXT2_FS=y CONFIG_EXT2_FS_XATTR=y CONFIG_EXT2_FS_POSIX_ACL=y @@ -253,12 +276,13 @@ CONFIG_XFS_POSIX_ACL=y CONFIG_BTRFS_FS=m CONFIG_BTRFS_FS_POSIX_ACL=y CONFIG_NILFS2_FS=m +CONFIG_FANOTIFY=y CONFIG_AUTOFS4_FS=m CONFIG_FUSE_FS=m CONFIG_OVERLAY_FS=m CONFIG_ISO9660_FS=y CONFIG_UDF_FS=m -CONFIG_MSDOS_FS=y +CONFIG_MSDOS_FS=m CONFIG_VFAT_FS=m CONFIG_PROC_KCORE=y CONFIG_TMPFS=y @@ -270,9 +294,9 @@ CONFIG_SQUASHFS_XATTR=y CONFIG_SQUASHFS_LZO=y CONFIG_SQUASHFS_XZ=y CONFIG_PSTORE=y -CONFIG_NFS_FS=y +CONFIG_NFS_FS=m CONFIG_NFS_V3_ACL=y -CONFIG_NFS_V4=y +CONFIG_NFS_V4=m CONFIG_NFSD=m CONFIG_NFSD_V3_ACL=y CONFIG_NFSD_V4=y @@ -291,9 +315,7 @@ CONFIG_DEBUG_STACKOVERFLOW=y CONFIG_SOFTLOCKUP_DETECTOR=y CONFIG_HARDLOCKUP_DETECTOR=y CONFIG_LATENCYTOP=y -CONFIG_FTRACE=y CONFIG_FUNCTION_TRACER=y -CONFIG_FUNCTION_GRAPH_TRACER=y CONFIG_SCHED_TRACER=y CONFIG_FTRACE_SYSCALLS=y CONFIG_BLK_DEV_IO_TRACE=y @@ -303,10 +325,10 @@ CONFIG_FTR_FIXUP_SELFTEST=y CONFIG_MSI_BITMAP_SELFTEST=y CONFIG_XMON=y CONFIG_CRYPTO_TEST=m -CONFIG_CRYPTO_CCM=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_HMAC=y CONFIG_CRYPTO_CRC32C_VPMSUM=m +CONFIG_CRYPTO_CRCT10DIF_VPMSUM=m CONFIG_CRYPTO_MD5_PPC=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_SHA1_PPC=m diff --git a/arch/powerpc/configs/wii_defconfig b/arch/powerpc/configs/wii_defconfig index 0b0f78823a1b..10940533da71 100644 --- a/arch/powerpc/configs/wii_defconfig +++ b/arch/powerpc/configs/wii_defconfig @@ -49,7 +49,9 @@ CONFIG_BLK_DEV_RAM_COUNT=2 CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y CONFIG_NETDEVICES=y +# CONFIG_ETHERNET is not set CONFIG_B43=y +CONFIG_B43_BUSES_SSB=y CONFIG_B43_SDIO=y # CONFIG_B43_PHY_LP is not set CONFIG_B43_DEBUG=y @@ -57,6 +59,7 @@ CONFIG_INPUT_FF_MEMLESS=m CONFIG_INPUT_JOYDEV=y CONFIG_INPUT_EVDEV=y # CONFIG_KEYBOARD_ATKBD is not set +CONFIG_KEYBOARD_GPIO=y # CONFIG_MOUSE_PS2 is not set CONFIG_INPUT_JOYSTICK=y CONFIG_INPUT_MISC=y @@ -71,6 +74,9 @@ CONFIG_I2C_CHARDEV=y CONFIG_I2C_GPIO=y CONFIG_GPIOLIB=y CONFIG_GPIO_SYSFS=y +CONFIG_GPIO_HLWD=y +CONFIG_POWER_RESET=y +CONFIG_POWER_RESET_GPIO=y # CONFIG_HWMON is not set CONFIG_SSB_DEBUG=y CONFIG_FB=y @@ -88,6 +94,14 @@ CONFIG_HID_APPLE=m CONFIG_HID_WACOM=m CONFIG_MMC=y CONFIG_MMC_SDHCI=y +CONFIG_MMC_SDHCI_PLTFM=y +CONFIG_MMC_SDHCI_OF_HLWD=y +CONFIG_NEW_LEDS=y +CONFIG_LEDS_CLASS=y +CONFIG_LEDS_GPIO=y +CONFIG_LEDS_TRIGGERS=y +CONFIG_LEDS_TRIGGER_HEARTBEAT=y +CONFIG_LEDS_TRIGGER_PANIC=y CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_GENERIC=y CONFIG_EXT2_FS=y diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h index d9713ad62e3c..aa9e785c59c2 100644 --- a/arch/powerpc/include/asm/asm-prototypes.h +++ b/arch/powerpc/include/asm/asm-prototypes.h @@ -36,8 +36,7 @@ void kexec_copy_flush(struct kimage *image); /* pseries hcall tracing */ extern struct static_key hcall_tracepoint_key; void __trace_hcall_entry(unsigned long opcode, unsigned long *args); -void __trace_hcall_exit(long opcode, unsigned long retval, - unsigned long *retbuf); +void __trace_hcall_exit(long opcode, long retval, unsigned long *retbuf); /* OPAL tracing */ #ifdef HAVE_JUMP_LABEL extern struct static_key opal_tracepoint_key; @@ -81,18 +80,12 @@ void machine_check_exception(struct pt_regs *regs); void emulation_assist_interrupt(struct pt_regs *regs); /* signals, syscalls and interrupts */ -#ifdef CONFIG_PPC64 -int sys_swapcontext(struct ucontext __user *old_ctx, - struct ucontext __user *new_ctx, - long ctx_size, long r6, long r7, long r8, struct pt_regs *regs); -#else long sys_swapcontext(struct ucontext __user *old_ctx, struct ucontext __user *new_ctx, - int ctx_size, int r6, int r7, int r8, struct pt_regs *regs); -int sys_debug_setcontext(struct ucontext __user *ctx, - int ndbg, struct sig_dbg_op __user *dbg, - int r6, int r7, int r8, - struct pt_regs *regs); + long ctx_size); +#ifdef CONFIG_PPC32 +long sys_debug_setcontext(struct ucontext __user *ctx, + int ndbg, struct sig_dbg_op __user *dbg); int ppc_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct timeval __user *tvp); unsigned long __init early_init(unsigned long dt_ptr); @@ -141,4 +134,7 @@ unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip); void pnv_power9_force_smt4_catch(void); void pnv_power9_force_smt4_release(void); +void tm_enable(void); +void tm_disable(void); +void tm_abort(uint8_t cause); #endif /* _ASM_POWERPC_ASM_PROTOTYPES_H */ diff --git a/arch/powerpc/include/asm/book3s/32/pgalloc.h b/arch/powerpc/include/asm/book3s/32/pgalloc.h index 5073cc75f1c8..6a6673907e45 100644 --- a/arch/powerpc/include/asm/book3s/32/pgalloc.h +++ b/arch/powerpc/include/asm/book3s/32/pgalloc.h @@ -99,6 +99,7 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage) static inline void pgtable_free(void *table, unsigned index_size) { if (!index_size) { + pgtable_page_dtor(virt_to_page(table)); free_page((unsigned long)table); } else { BUG_ON(index_size > MAX_PGTABLE_INDEX_SIZE); diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h index 4b5423030d4b..9a3798660cef 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-4k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h @@ -38,8 +38,12 @@ #define H_PAGE_4K_PFN 0x0 #define H_PAGE_THP_HUGE 0x0 #define H_PAGE_COMBO 0x0 -#define H_PTE_FRAG_NR 0 -#define H_PTE_FRAG_SIZE_SHIFT 0 + +/* 8 bytes per each pte entry */ +#define H_PTE_FRAG_SIZE_SHIFT (H_PTE_INDEX_SIZE + 3) +#define H_PTE_FRAG_NR (PAGE_SIZE >> H_PTE_FRAG_SIZE_SHIFT) +#define H_PMD_FRAG_SIZE_SHIFT (H_PMD_INDEX_SIZE + 3) +#define H_PMD_FRAG_NR (PAGE_SIZE >> H_PMD_FRAG_SIZE_SHIFT) /* memory key bits, only 8 keys supported */ #define H_PTE_PKEY_BIT0 0 diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h index cc82745355b3..c81793d47af9 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-64k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h @@ -46,6 +46,13 @@ #define H_PTE_FRAG_SIZE_SHIFT (H_PTE_INDEX_SIZE + 3 + 1) #define H_PTE_FRAG_NR (PAGE_SIZE >> H_PTE_FRAG_SIZE_SHIFT) +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLB_PAGE) +#define H_PMD_FRAG_SIZE_SHIFT (H_PMD_INDEX_SIZE + 3 + 1) +#else +#define H_PMD_FRAG_SIZE_SHIFT (H_PMD_INDEX_SIZE + 3) +#endif +#define H_PMD_FRAG_NR (PAGE_SIZE >> H_PMD_FRAG_SIZE_SHIFT) + #ifndef __ASSEMBLY__ #include <asm/errno.h> diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h index cc8cd656ccfe..0387b155f13d 100644 --- a/arch/powerpc/include/asm/book3s/64/hash.h +++ b/arch/powerpc/include/asm/book3s/64/hash.h @@ -23,16 +23,6 @@ H_PUD_INDEX_SIZE + H_PGD_INDEX_SIZE + PAGE_SHIFT) #define H_PGTABLE_RANGE (ASM_CONST(1) << H_PGTABLE_EADDR_SIZE) -#if (defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLB_PAGE)) && \ - defined(CONFIG_PPC_64K_PAGES) -/* - * only with hash 64k we need to use the second half of pmd page table - * to store pointer to deposited pgtable_t - */ -#define H_PMD_CACHE_INDEX (H_PMD_INDEX_SIZE + 1) -#else -#define H_PMD_CACHE_INDEX H_PMD_INDEX_SIZE -#endif /* * We store the slot details in the second half of page table. * Increase the pud level table so that hugetlb ptes can be stored diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h index 5094696eecd6..9c8c669a6b6a 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu.h +++ b/arch/powerpc/include/asm/book3s/64/mmu.h @@ -134,10 +134,11 @@ typedef struct { #ifdef CONFIG_PPC_SUBPAGE_PROT struct subpage_prot_table spt; #endif /* CONFIG_PPC_SUBPAGE_PROT */ -#ifdef CONFIG_PPC_64K_PAGES - /* for 4K PTE fragment support */ + /* + * pagetable fragment support + */ void *pte_frag; -#endif + void *pmd_frag; #ifdef CONFIG_SPAPR_TCE_IOMMU struct list_head iommu_group_mem_list; #endif diff --git a/arch/powerpc/include/asm/book3s/64/pgalloc.h b/arch/powerpc/include/asm/book3s/64/pgalloc.h index 558a159600ad..01ee40f11f3a 100644 --- a/arch/powerpc/include/asm/book3s/64/pgalloc.h +++ b/arch/powerpc/include/asm/book3s/64/pgalloc.h @@ -42,7 +42,9 @@ extern struct kmem_cache *pgtable_cache[]; }) extern pte_t *pte_fragment_alloc(struct mm_struct *, unsigned long, int); +extern pmd_t *pmd_fragment_alloc(struct mm_struct *, unsigned long); extern void pte_fragment_free(unsigned long *, int); +extern void pmd_fragment_free(unsigned long *); extern void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift); #ifdef CONFIG_SMP extern void __tlb_remove_table(void *_table); @@ -88,8 +90,7 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm) * need to do this for 4k. */ #if defined(CONFIG_HUGETLB_PAGE) && defined(CONFIG_PPC_64K_PAGES) && \ - ((H_PGD_INDEX_SIZE == H_PUD_CACHE_INDEX) || \ - (H_PGD_INDEX_SIZE == H_PMD_CACHE_INDEX)) + (H_PGD_INDEX_SIZE == H_PUD_CACHE_INDEX) memset(pgd, 0, PGD_TABLE_SIZE); #endif return pgd; @@ -124,36 +125,35 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) } static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud, - unsigned long address) + unsigned long address) { /* * By now all the pud entries should be none entries. So go * ahead and flush the page walk cache */ flush_tlb_pgtable(tlb, address); - pgtable_free_tlb(tlb, pud, PUD_CACHE_INDEX); + pgtable_free_tlb(tlb, pud, PUD_INDEX); } static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) { - return kmem_cache_alloc(PGT_CACHE(PMD_CACHE_INDEX), - pgtable_gfp_flags(mm, GFP_KERNEL)); + return pmd_fragment_alloc(mm, addr); } static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) { - kmem_cache_free(PGT_CACHE(PMD_CACHE_INDEX), pmd); + pmd_fragment_free((unsigned long *)pmd); } static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd, - unsigned long address) + unsigned long address) { /* * By now all the pud entries should be none entries. So go * ahead and flush the page walk cache */ flush_tlb_pgtable(tlb, address); - return pgtable_free_tlb(tlb, pmd, PMD_CACHE_INDEX); + return pgtable_free_tlb(tlb, pmd, PMD_INDEX); } static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, @@ -173,31 +173,6 @@ static inline pgtable_t pmd_pgtable(pmd_t pmd) return (pgtable_t)pmd_page_vaddr(pmd); } -#ifdef CONFIG_PPC_4K_PAGES -static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, - unsigned long address) -{ - return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO); -} - -static inline pgtable_t pte_alloc_one(struct mm_struct *mm, - unsigned long address) -{ - struct page *page; - pte_t *pte; - - pte = (pte_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO | __GFP_ACCOUNT); - if (!pte) - return NULL; - page = virt_to_page(pte); - if (!pgtable_page_ctor(page)) { - __free_page(page); - return NULL; - } - return pte; -} -#else /* if CONFIG_PPC_64K_PAGES */ - static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) { @@ -209,7 +184,6 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm, { return (pgtable_t)pte_fragment_alloc(mm, address, 0); } -#endif static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) { @@ -229,7 +203,7 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table, * ahead and flush the page walk cache */ flush_tlb_pgtable(tlb, address); - pgtable_free_tlb(tlb, table, 0); + pgtable_free_tlb(tlb, table, PTE_INDEX); } #define check_pgt_cache() do { } while (0) diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 47b5ffc8715d..c233915abb68 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -212,13 +212,13 @@ extern unsigned long __pte_index_size; extern unsigned long __pmd_index_size; extern unsigned long __pud_index_size; extern unsigned long __pgd_index_size; -extern unsigned long __pmd_cache_index; extern unsigned long __pud_cache_index; #define PTE_INDEX_SIZE __pte_index_size #define PMD_INDEX_SIZE __pmd_index_size #define PUD_INDEX_SIZE __pud_index_size #define PGD_INDEX_SIZE __pgd_index_size -#define PMD_CACHE_INDEX __pmd_cache_index +/* pmd table use page table fragments */ +#define PMD_CACHE_INDEX 0 #define PUD_CACHE_INDEX __pud_cache_index /* * Because of use of pte fragments and THP, size of page table @@ -246,6 +246,12 @@ extern unsigned long __pte_frag_size_shift; #define PTE_FRAG_SIZE_SHIFT __pte_frag_size_shift #define PTE_FRAG_SIZE (1UL << PTE_FRAG_SIZE_SHIFT) +extern unsigned long __pmd_frag_nr; +#define PMD_FRAG_NR __pmd_frag_nr +extern unsigned long __pmd_frag_size_shift; +#define PMD_FRAG_SIZE_SHIFT __pmd_frag_size_shift +#define PMD_FRAG_SIZE (1UL << PMD_FRAG_SIZE_SHIFT) + #define PTRS_PER_PTE (1 << PTE_INDEX_SIZE) #define PTRS_PER_PMD (1 << PMD_INDEX_SIZE) #define PTRS_PER_PUD (1 << PUD_INDEX_SIZE) @@ -273,6 +279,16 @@ extern unsigned long __pte_frag_size_shift; /* Bits to mask out from a PGD to get to the PUD page */ #define PGD_MASKED_BITS 0xc0000000000000ffUL +/* + * Used as an indicator for rcu callback functions + */ +enum pgtable_index { + PTE_INDEX = 0, + PMD_INDEX, + PUD_INDEX, + PGD_INDEX, +}; + extern unsigned long __vmalloc_start; extern unsigned long __vmalloc_end; #define VMALLOC_START __vmalloc_start diff --git a/arch/powerpc/include/asm/book3s/64/radix-4k.h b/arch/powerpc/include/asm/book3s/64/radix-4k.h index ca366ec86310..863c3e8286fb 100644 --- a/arch/powerpc/include/asm/book3s/64/radix-4k.h +++ b/arch/powerpc/include/asm/book3s/64/radix-4k.h @@ -15,4 +15,7 @@ #define RADIX_PTE_FRAG_SIZE_SHIFT (RADIX_PTE_INDEX_SIZE + 3) #define RADIX_PTE_FRAG_NR (PAGE_SIZE >> RADIX_PTE_FRAG_SIZE_SHIFT) +#define RADIX_PMD_FRAG_SIZE_SHIFT (RADIX_PMD_INDEX_SIZE + 3) +#define RADIX_PMD_FRAG_NR (PAGE_SIZE >> RADIX_PMD_FRAG_SIZE_SHIFT) + #endif /* _ASM_POWERPC_PGTABLE_RADIX_4K_H */ diff --git a/arch/powerpc/include/asm/book3s/64/radix-64k.h b/arch/powerpc/include/asm/book3s/64/radix-64k.h index 830082496876..ccb78ca9d0c5 100644 --- a/arch/powerpc/include/asm/book3s/64/radix-64k.h +++ b/arch/powerpc/include/asm/book3s/64/radix-64k.h @@ -16,4 +16,8 @@ */ #define RADIX_PTE_FRAG_SIZE_SHIFT (RADIX_PTE_INDEX_SIZE + 3) #define RADIX_PTE_FRAG_NR (PAGE_SIZE >> RADIX_PTE_FRAG_SIZE_SHIFT) + +#define RADIX_PMD_FRAG_SIZE_SHIFT (RADIX_PMD_INDEX_SIZE + 3) +#define RADIX_PMD_FRAG_NR (PAGE_SIZE >> RADIX_PMD_FRAG_SIZE_SHIFT) + #endif /* _ASM_POWERPC_PGTABLE_RADIX_64K_H */ diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h index 19b45ba6caf9..ef5c3f2994c9 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h @@ -51,4 +51,11 @@ extern void radix__flush_tlb_all(void); extern void radix__flush_tlb_pte_p9_dd1(unsigned long old_pte, struct mm_struct *mm, unsigned long address); +extern void radix__flush_tlb_lpid_page(unsigned int lpid, + unsigned long addr, + unsigned long page_size); +extern void radix__flush_pwc_lpid(unsigned int lpid); +extern void radix__local_flush_tlb_lpid(unsigned int lpid); +extern void radix__local_flush_tlb_lpid_guest(unsigned int lpid); + #endif diff --git a/arch/powerpc/include/asm/checksum.h b/arch/powerpc/include/asm/checksum.h index 842124b199b5..4e63787dc3be 100644 --- a/arch/powerpc/include/asm/checksum.h +++ b/arch/powerpc/include/asm/checksum.h @@ -112,7 +112,7 @@ static inline __wsum csum_add(__wsum csum, __wsum addend) #ifdef __powerpc64__ res += (__force u64)addend; - return (__force __wsum) from64to32(res); + return (__force __wsum)((u32)res + (res >> 32)); #else asm("addc %0,%0,%1;" "addze %0,%0;" diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h index 9abddde372ab..fc3a2203c566 100644 --- a/arch/powerpc/include/asm/ftrace.h +++ b/arch/powerpc/include/asm/ftrace.h @@ -48,9 +48,6 @@ #else /* !__ASSEMBLY__ */ extern void _mcount(void); -#ifdef CONFIG_DYNAMIC_FTRACE -# define FTRACE_ADDR ((unsigned long)ftrace_caller) -# define FTRACE_REGS_ADDR FTRACE_ADDR static inline unsigned long ftrace_call_adjust(unsigned long addr) { /* reloction of mcount call site is the same as the address */ @@ -60,16 +57,15 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr) struct dyn_arch_ftrace { struct module *mod; }; -#endif /* CONFIG_DYNAMIC_FTRACE */ #endif /* __ASSEMBLY__ */ #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS #define ARCH_SUPPORTS_FTRACE_OPS 1 #endif -#endif +#endif /* CONFIG_FUNCTION_TRACER */ -#if defined(CONFIG_FTRACE_SYSCALLS) && !defined(__ASSEMBLY__) -#ifdef PPC64_ELF_ABI_v1 +#ifndef __ASSEMBLY__ +#if defined(CONFIG_FTRACE_SYSCALLS) && defined(PPC64_ELF_ABI_v1) #define ARCH_HAS_SYSCALL_MATCH_SYM_NAME static inline bool arch_syscall_match_sym_name(const char *sym, const char *name) { @@ -81,7 +77,24 @@ static inline bool arch_syscall_match_sym_name(const char *sym, const char *name */ return !strcmp(sym + 4, name + 3); } -#endif -#endif /* CONFIG_FTRACE_SYSCALLS && !__ASSEMBLY__ */ +#endif /* CONFIG_FTRACE_SYSCALLS && PPC64_ELF_ABI_v1 */ + +#ifdef CONFIG_PPC64 +#include <asm/paca.h> + +static inline void this_cpu_disable_ftrace(void) +{ + get_paca()->ftrace_enabled = 0; +} + +static inline void this_cpu_enable_ftrace(void) +{ + get_paca()->ftrace_enabled = 1; +} +#else /* CONFIG_PPC64 */ +static inline void this_cpu_disable_ftrace(void) { } +static inline void this_cpu_enable_ftrace(void) { } +#endif /* CONFIG_PPC64 */ +#endif /* !__ASSEMBLY__ */ #endif /* _ASM_POWERPC_FTRACE */ diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h index 78540c074d70..96444bc08034 100644 --- a/arch/powerpc/include/asm/hugetlb.h +++ b/arch/powerpc/include/asm/hugetlb.h @@ -202,7 +202,7 @@ static inline void flush_hugetlb_page(struct vm_area_struct *vma, static inline pte_t *hugepte_offset(hugepd_t hpd, unsigned long addr, unsigned pdshift) { - return 0; + return NULL; } #endif /* CONFIG_HUGETLB_PAGE */ diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h index af074923d598..e0331e754568 100644 --- a/arch/powerpc/include/asm/io.h +++ b/arch/powerpc/include/asm/io.h @@ -367,6 +367,11 @@ static inline void __raw_writeq(unsigned long v, volatile void __iomem *addr) *(volatile unsigned long __force *)PCI_FIX_ADDR(addr) = v; } +static inline void __raw_writeq_be(unsigned long v, volatile void __iomem *addr) +{ + __raw_writeq((__force unsigned long)cpu_to_be64(v), addr); +} + /* * Real mode versions of the above. Those instructions are only supposed * to be used in hypervisor real mode as per the architecture spec. @@ -395,6 +400,11 @@ static inline void __raw_rm_writeq(u64 val, volatile void __iomem *paddr) : : "r" (val), "r" (paddr) : "memory"); } +static inline void __raw_rm_writeq_be(u64 val, volatile void __iomem *paddr) +{ + __raw_rm_writeq((__force u64)cpu_to_be64(val), paddr); +} + static inline u8 __raw_rm_readb(volatile void __iomem *paddr) { u8 ret; diff --git a/arch/powerpc/include/asm/mmu-book3e.h b/arch/powerpc/include/asm/mmu-book3e.h index cda94a0f5146..e20072972e35 100644 --- a/arch/powerpc/include/asm/mmu-book3e.h +++ b/arch/powerpc/include/asm/mmu-book3e.h @@ -230,10 +230,6 @@ typedef struct { unsigned int id; unsigned int active; unsigned long vdso_base; -#ifdef CONFIG_PPC_64K_PAGES - /* for 4K PTE fragment support */ - void *pte_frag; -#endif } mm_context_t; /* Page size definitions, common between 32 and 64-bit @@ -275,8 +271,6 @@ static inline unsigned int mmu_psize_to_shift(unsigned int mmu_psize) */ #if defined(CONFIG_PPC_4K_PAGES) #define mmu_virtual_psize MMU_PAGE_4K -#elif defined(CONFIG_PPC_64K_PAGES) -#define mmu_virtual_psize MMU_PAGE_64K #else #error Unsupported page size #endif diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h index 4f6573934792..d8374f984f39 100644 --- a/arch/powerpc/include/asm/module.h +++ b/arch/powerpc/include/asm/module.h @@ -50,10 +50,6 @@ struct mod_arch_specific { unsigned int stubs_section; /* Index of stubs section in module */ unsigned int toc_section; /* What section is the TOC? */ bool toc_fixed; /* Have we fixed up .TOC.? */ -#ifdef CONFIG_DYNAMIC_FTRACE - unsigned long toc; - unsigned long tramp; -#endif /* For module function descriptor dereference */ unsigned long start_opd; @@ -62,10 +58,14 @@ struct mod_arch_specific { /* Indices of PLT sections within module. */ unsigned int core_plt_section; unsigned int init_plt_section; +#endif /* powerpc64 */ + #ifdef CONFIG_DYNAMIC_FTRACE unsigned long tramp; +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS + unsigned long tramp_regs; +#endif #endif -#endif /* powerpc64 */ /* List of BUG addresses, source line numbers and filenames */ struct list_head bug_list; diff --git a/arch/powerpc/include/asm/mpc52xx.h b/arch/powerpc/include/asm/mpc52xx.h index e94cede14522..ce1e0aabaa64 100644 --- a/arch/powerpc/include/asm/mpc52xx.h +++ b/arch/powerpc/include/asm/mpc52xx.h @@ -350,14 +350,14 @@ extern struct mpc52xx_suspend mpc52xx_suspend; extern int __init mpc52xx_pm_init(void); extern int mpc52xx_set_wakeup_gpio(u8 pin, u8 level); -#ifdef CONFIG_PPC_LITE5200 -extern int __init lite5200_pm_init(void); - /* lite5200 calls mpc5200 suspend functions, so here they are */ extern int mpc52xx_pm_prepare(void); extern int mpc52xx_pm_enter(suspend_state_t); extern void mpc52xx_pm_finish(void); extern char saved_sram[0x4000]; /* reuse buffer from mpc52xx suspend */ + +#ifdef CONFIG_PPC_LITE5200 +int __init lite5200_pm_init(void); #endif #endif /* CONFIG_PM */ diff --git a/arch/powerpc/include/asm/nohash/32/pgalloc.h b/arch/powerpc/include/asm/nohash/32/pgalloc.h index 29d37bd1f3b3..1707781d2f20 100644 --- a/arch/powerpc/include/asm/nohash/32/pgalloc.h +++ b/arch/powerpc/include/asm/nohash/32/pgalloc.h @@ -100,6 +100,7 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage) static inline void pgtable_free(void *table, unsigned index_size) { if (!index_size) { + pgtable_page_dtor(virt_to_page(table)); free_page((unsigned long)table); } else { BUG_ON(index_size > MAX_PGTABLE_INDEX_SIZE); diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h index 03bbd1149530..987a658b18e1 100644 --- a/arch/powerpc/include/asm/nohash/32/pgtable.h +++ b/arch/powerpc/include/asm/nohash/32/pgtable.h @@ -133,7 +133,7 @@ extern int icache_44x_need_flush; #ifndef __ASSEMBLY__ #define pte_clear(mm, addr, ptep) \ - do { pte_update(ptep, ~_PAGE_HASHPTE, 0); } while (0) + do { pte_update(ptep, ~0, 0); } while (0) #define pmd_none(pmd) (!pmd_val(pmd)) #define pmd_bad(pmd) (pmd_val(pmd) & _PMD_BAD) @@ -146,21 +146,6 @@ static inline void pmd_clear(pmd_t *pmdp) /* - * When flushing the tlb entry for a page, we also need to flush the hash - * table entry. flush_hash_pages is assembler (for speed) in hashtable.S. - */ -extern int flush_hash_pages(unsigned context, unsigned long va, - unsigned long pmdval, int count); - -/* Add an HPTE to the hash table */ -extern void add_hash_page(unsigned context, unsigned long va, - unsigned long pmdval); - -/* Flush an entry from the TLB/hash table */ -extern void flush_hash_entry(struct mm_struct *mm, pte_t *ptep, - unsigned long address); - -/* * PTE updates. This function is called whenever an existing * valid PTE is updated. This does -not- include set_pte_at() * which nowadays only sets a new PTE. @@ -246,12 +231,6 @@ static inline int __ptep_test_and_clear_young(unsigned int context, unsigned lon { unsigned long old; old = pte_update(ptep, _PAGE_ACCESSED, 0); -#if _PAGE_HASHPTE != 0 - if (old & _PAGE_HASHPTE) { - unsigned long ptephys = __pa(ptep) & PAGE_MASK; - flush_hash_pages(context, addr, ptephys, 1); - } -#endif return (old & _PAGE_ACCESSED) != 0; } #define ptep_test_and_clear_young(__vma, __addr, __ptep) \ @@ -261,7 +240,7 @@ static inline int __ptep_test_and_clear_young(unsigned int context, unsigned lon static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - return __pte(pte_update(ptep, ~_PAGE_HASHPTE, 0)); + return __pte(pte_update(ptep, ~0, 0)); } #define __HAVE_ARCH_PTEP_SET_WRPROTECT @@ -288,8 +267,13 @@ static inline void __ptep_set_access_flags(struct mm_struct *mm, pte_update(ptep, clr, set); } +static inline int pte_young(pte_t pte) +{ + return pte_val(pte) & _PAGE_ACCESSED; +} + #define __HAVE_ARCH_PTE_SAME -#define pte_same(A,B) (((pte_val(A) ^ pte_val(B)) & ~_PAGE_HASHPTE) == 0) +#define pte_same(A,B) ((pte_val(A) ^ pte_val(B)) == 0) /* * Note that on Book E processors, the pmd contains the kernel virtual @@ -330,7 +314,7 @@ static inline void __ptep_set_access_flags(struct mm_struct *mm, /* * Encode and decode a swap entry. * Note that the bits we use in a PTE for representing a swap entry - * must not include the _PAGE_PRESENT bit or the _PAGE_HASHPTE bit (if used). + * must not include the _PAGE_PRESENT bit. * -- paulus */ #define __swp_type(entry) ((entry).val & 0x1f) diff --git a/arch/powerpc/include/asm/nohash/32/pte-40x.h b/arch/powerpc/include/asm/nohash/32/pte-40x.h index 124f9ac23a1e..bb4b3a4b92a0 100644 --- a/arch/powerpc/include/asm/nohash/32/pte-40x.h +++ b/arch/powerpc/include/asm/nohash/32/pte-40x.h @@ -52,12 +52,9 @@ #define _PMD_PRESENT 0x400 /* PMD points to page of PTEs */ #define _PMD_BAD 0x802 -#define _PMD_SIZE 0x0e0 /* size field, != 0 for large-page PMD entry */ #define _PMD_SIZE_4M 0x0c0 #define _PMD_SIZE_16M 0x0e0 -#define PMD_PAGE_SIZE(pmdval) (1024 << (((pmdval) & _PMD_SIZE) >> 4)) - /* Until my rework is finished, 40x still needs atomic PTE updates */ #define PTE_ATOMIC_UPDATES 1 diff --git a/arch/powerpc/include/asm/nohash/64/pgalloc.h b/arch/powerpc/include/asm/nohash/64/pgalloc.h index 9721c7867b9c..0e693f322cb2 100644 --- a/arch/powerpc/include/asm/nohash/64/pgalloc.h +++ b/arch/powerpc/include/asm/nohash/64/pgalloc.h @@ -52,8 +52,6 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) kmem_cache_free(PGT_CACHE(PGD_INDEX_SIZE), pgd); } -#ifndef CONFIG_PPC_64K_PAGES - #define pgd_populate(MM, PGD, PUD) pgd_set(PGD, (unsigned long)PUD) static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) @@ -86,6 +84,18 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, #define pmd_pgtable(pmd) pmd_page(pmd) +static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) +{ + return kmem_cache_alloc(PGT_CACHE(PMD_CACHE_INDEX), + pgtable_gfp_flags(mm, GFP_KERNEL)); +} + +static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) +{ + kmem_cache_free(PGT_CACHE(PMD_CACHE_INDEX), pmd); +} + + static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) { @@ -120,84 +130,47 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage) __free_page(ptepage); } -extern void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift); -#ifdef CONFIG_SMP -extern void __tlb_remove_table(void *_table); -#endif -static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table, - unsigned long address) +static inline void pgtable_free(void *table, int shift) { - tlb_flush_pgtable(tlb, address); - pgtable_free_tlb(tlb, page_address(table), 0); + if (!shift) { + pgtable_page_dtor(virt_to_page(table)); + free_page((unsigned long)table); + } else { + BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE); + kmem_cache_free(PGT_CACHE(shift), table); + } } -#else /* if CONFIG_PPC_64K_PAGES */ - -extern pte_t *pte_fragment_alloc(struct mm_struct *, unsigned long, int); -extern void pte_fragment_free(unsigned long *, int); -extern void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift); #ifdef CONFIG_SMP -extern void __tlb_remove_table(void *_table); -#endif - -#define pud_populate(mm, pud, pmd) pud_set(pud, (unsigned long)pmd) - -static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, - pte_t *pte) +static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift) { - pmd_set(pmd, (unsigned long)pte); -} + unsigned long pgf = (unsigned long)table; -static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, - pgtable_t pte_page) -{ - pmd_set(pmd, (unsigned long)pte_page); + BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE); + pgf |= shift; + tlb_remove_table(tlb, (void *)pgf); } -static inline pgtable_t pmd_pgtable(pmd_t pmd) +static inline void __tlb_remove_table(void *_table) { - return (pgtable_t)(pmd_val(pmd) & ~PMD_MASKED_BITS); -} + void *table = (void *)((unsigned long)_table & ~MAX_PGTABLE_INDEX_SIZE); + unsigned shift = (unsigned long)_table & MAX_PGTABLE_INDEX_SIZE; -static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, - unsigned long address) -{ - return (pte_t *)pte_fragment_alloc(mm, address, 1); + pgtable_free(table, shift); } -static inline pgtable_t pte_alloc_one(struct mm_struct *mm, - unsigned long address) -{ - return (pgtable_t)pte_fragment_alloc(mm, address, 0); -} - -static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) -{ - pte_fragment_free((unsigned long *)pte, 1); -} - -static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage) +#else +static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift) { - pte_fragment_free((unsigned long *)ptepage, 0); + pgtable_free(table, shift); } +#endif static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table, unsigned long address) { tlb_flush_pgtable(tlb, address); - pgtable_free_tlb(tlb, table, 0); -} -#endif /* CONFIG_PPC_64K_PAGES */ - -static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) -{ - return kmem_cache_alloc(PGT_CACHE(PMD_CACHE_INDEX), - pgtable_gfp_flags(mm, GFP_KERNEL)); -} - -static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) -{ - kmem_cache_free(PGT_CACHE(PMD_CACHE_INDEX), pmd); + pgtable_free_tlb(tlb, page_address(table), 0); } #define __pmd_free_tlb(tlb, pmd, addr) \ diff --git a/arch/powerpc/include/asm/nohash/64/pgtable-64k.h b/arch/powerpc/include/asm/nohash/64/pgtable-64k.h deleted file mode 100644 index 7210c2818e41..000000000000 --- a/arch/powerpc/include/asm/nohash/64/pgtable-64k.h +++ /dev/null @@ -1,57 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_POWERPC_NOHASH_64_PGTABLE_64K_H -#define _ASM_POWERPC_NOHASH_64_PGTABLE_64K_H - -#define __ARCH_USE_5LEVEL_HACK -#include <asm-generic/pgtable-nopud.h> - - -#define PTE_INDEX_SIZE 8 -#define PMD_INDEX_SIZE 10 -#define PUD_INDEX_SIZE 0 -#define PGD_INDEX_SIZE 12 - -/* - * we support 32 fragments per PTE page of 64K size - */ -#define PTE_FRAG_NR 32 -/* - * We use a 2K PTE page fragment and another 2K for storing - * real_pte_t hash index - */ -#define PTE_FRAG_SIZE_SHIFT 11 -#define PTE_FRAG_SIZE (1UL << PTE_FRAG_SIZE_SHIFT) - -#ifndef __ASSEMBLY__ -#define PTE_TABLE_SIZE PTE_FRAG_SIZE -#define PMD_TABLE_SIZE (sizeof(pmd_t) << PMD_INDEX_SIZE) -#define PUD_TABLE_SIZE (0) -#define PGD_TABLE_SIZE (sizeof(pgd_t) << PGD_INDEX_SIZE) -#endif /* __ASSEMBLY__ */ - -#define PTRS_PER_PTE (1 << PTE_INDEX_SIZE) -#define PTRS_PER_PMD (1 << PMD_INDEX_SIZE) -#define PTRS_PER_PGD (1 << PGD_INDEX_SIZE) - -/* PMD_SHIFT determines what a second-level page table entry can map */ -#define PMD_SHIFT (PAGE_SHIFT + PTE_INDEX_SIZE) -#define PMD_SIZE (1UL << PMD_SHIFT) -#define PMD_MASK (~(PMD_SIZE-1)) - -/* PGDIR_SHIFT determines what a third-level page table entry can map */ -#define PGDIR_SHIFT (PMD_SHIFT + PMD_INDEX_SIZE) -#define PGDIR_SIZE (1UL << PGDIR_SHIFT) -#define PGDIR_MASK (~(PGDIR_SIZE-1)) - -/* - * Bits to mask out from a PMD to get to the PTE page - * PMDs point to PTE table fragments which are PTE_FRAG_SIZE aligned. - */ -#define PMD_MASKED_BITS (PTE_FRAG_SIZE - 1) -/* Bits to mask out from a PGD/PUD to get to the PMD page */ -#define PUD_MASKED_BITS 0x1ff - -#define pgd_pte(pgd) (pud_pte(((pud_t){ pgd }))) -#define pte_pgd(pte) ((pgd_t)pte_pud(pte)) - -#endif /* _ASM_POWERPC_NOHASH_64_PGTABLE_64K_H */ diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h index 5c5f75d005ad..de78eda5f841 100644 --- a/arch/powerpc/include/asm/nohash/64/pgtable.h +++ b/arch/powerpc/include/asm/nohash/64/pgtable.h @@ -6,13 +6,13 @@ * the ppc64 hashed page table. */ -#ifdef CONFIG_PPC_64K_PAGES -#include <asm/nohash/64/pgtable-64k.h> -#else #include <asm/nohash/64/pgtable-4k.h> -#endif #include <asm/barrier.h> +#ifdef CONFIG_PPC_64K_PAGES +#error "Page size not supported" +#endif + #define FIRST_USER_ADDRESS 0UL /* @@ -173,8 +173,6 @@ static inline void pgd_set(pgd_t *pgdp, unsigned long val) /* to find an entry in a kernel page-table-directory */ /* This now only contains the vmalloc pages */ #define pgd_offset_k(address) pgd_offset(&init_mm, address) -extern void hpte_need_flush(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, unsigned long pte, int huge); /* Atomic PTE updates */ static inline unsigned long pte_update(struct mm_struct *mm, @@ -188,14 +186,12 @@ static inline unsigned long pte_update(struct mm_struct *mm, __asm__ __volatile__( "1: ldarx %0,0,%3 # pte_update\n\ - andi. %1,%0,%6\n\ - bne- 1b \n\ andc %1,%0,%4 \n\ - or %1,%1,%7\n\ + or %1,%1,%6\n\ stdcx. %1,0,%3 \n\ bne- 1b" : "=&r" (old), "=&r" (tmp), "=m" (*ptep) - : "r" (ptep), "r" (clr), "m" (*ptep), "i" (_PAGE_BUSY), "r" (set) + : "r" (ptep), "r" (clr), "m" (*ptep), "r" (set) : "cc" ); #else unsigned long old = pte_val(*ptep); @@ -205,20 +201,20 @@ static inline unsigned long pte_update(struct mm_struct *mm, if (!huge) assert_pte_locked(mm, addr); -#ifdef CONFIG_PPC_BOOK3S_64 - if (old & _PAGE_HASHPTE) - hpte_need_flush(mm, addr, ptep, old, huge); -#endif - return old; } +static inline int pte_young(pte_t pte) +{ + return pte_val(pte) & _PAGE_ACCESSED; +} + static inline int __ptep_test_and_clear_young(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { unsigned long old; - if ((pte_val(*ptep) & (_PAGE_ACCESSED | _PAGE_HASHPTE)) == 0) + if (pte_young(*ptep)) return 0; old = pte_update(mm, addr, ptep, _PAGE_ACCESSED, 0, 0); return (old & _PAGE_ACCESSED) != 0; @@ -297,13 +293,11 @@ static inline void __ptep_set_access_flags(struct mm_struct *mm, __asm__ __volatile__( "1: ldarx %0,0,%4\n\ - andi. %1,%0,%6\n\ - bne- 1b \n\ or %0,%3,%0\n\ stdcx. %0,0,%4\n\ bne- 1b" :"=&r" (old), "=&r" (tmp), "=m" (*ptep) - :"r" (bits), "r" (ptep), "m" (*ptep), "i" (_PAGE_BUSY) + :"r" (bits), "r" (ptep), "m" (*ptep) :"cc"); #else unsigned long old = pte_val(*ptep); @@ -312,7 +306,7 @@ static inline void __ptep_set_access_flags(struct mm_struct *mm, } #define __HAVE_ARCH_PTE_SAME -#define pte_same(A,B) (((pte_val(A) ^ pte_val(B)) & ~_PAGE_HPTEFLAGS) == 0) +#define pte_same(A,B) ((pte_val(A) ^ pte_val(B)) == 0) #define pte_ERROR(e) \ pr_err("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, pte_val(e)) @@ -324,11 +318,6 @@ static inline void __ptep_set_access_flags(struct mm_struct *mm, /* Encode and de-code a swap entry */ #define MAX_SWAPFILES_CHECK() do { \ BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS); \ - /* \ - * Don't have overlapping bits with _PAGE_HPTEFLAGS \ - * We filter HPTEFLAGS on set_pte. \ - */ \ - BUILD_BUG_ON(_PAGE_HPTEFLAGS & (0x1f << _PAGE_BIT_SWAP_TYPE)); \ } while (0) /* * on pte we don't need handle RADIX_TREE_EXCEPTIONAL_SHIFT; diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h index c56de1e8026f..2160be2e4339 100644 --- a/arch/powerpc/include/asm/nohash/pgtable.h +++ b/arch/powerpc/include/asm/nohash/pgtable.h @@ -17,7 +17,6 @@ static inline int pte_write(pte_t pte) } static inline int pte_read(pte_t pte) { return 1; } static inline int pte_dirty(pte_t pte) { return pte_val(pte) & _PAGE_DIRTY; } -static inline int pte_young(pte_t pte) { return pte_val(pte) & _PAGE_ACCESSED; } static inline int pte_special(pte_t pte) { return pte_val(pte) & _PAGE_SPECIAL; } static inline int pte_none(pte_t pte) { return (pte_val(pte) & ~_PTE_NONE_MASK) == 0; } static inline pgprot_t pte_pgprot(pte_t pte) { return __pgprot(pte_val(pte) & PAGE_PROT_BITS); } @@ -148,70 +147,33 @@ extern void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, int percpu) { -#if defined(CONFIG_PPC_STD_MMU_32) && defined(CONFIG_SMP) && !defined(CONFIG_PTE_64BIT) - /* First case is 32-bit Hash MMU in SMP mode with 32-bit PTEs. We use the - * helper pte_update() which does an atomic update. We need to do that - * because a concurrent invalidation can clear _PAGE_HASHPTE. If it's a - * per-CPU PTE such as a kmap_atomic, we do a simple update preserving - * the hash bits instead (ie, same as the non-SMP case) - */ - if (percpu) - *ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE) - | (pte_val(pte) & ~_PAGE_HASHPTE)); - else - pte_update(ptep, ~_PAGE_HASHPTE, pte_val(pte)); - -#elif defined(CONFIG_PPC32) && defined(CONFIG_PTE_64BIT) /* Second case is 32-bit with 64-bit PTE. In this case, we * can just store as long as we do the two halves in the right order - * with a barrier in between. This is possible because we take care, - * in the hash code, to pre-invalidate if the PTE was already hashed, - * which synchronizes us with any concurrent invalidation. - * In the percpu case, we also fallback to the simple update preserving - * the hash bits + * with a barrier in between. + * In the percpu case, we also fallback to the simple update */ - if (percpu) { - *ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE) - | (pte_val(pte) & ~_PAGE_HASHPTE)); + if (IS_ENABLED(CONFIG_PPC32) && IS_ENABLED(CONFIG_PTE_64BIT) && !percpu) { + __asm__ __volatile__("\ + stw%U0%X0 %2,%0\n\ + eieio\n\ + stw%U0%X0 %L2,%1" + : "=m" (*ptep), "=m" (*((unsigned char *)ptep+4)) + : "r" (pte) : "memory"); return; } -#if _PAGE_HASHPTE != 0 - if (pte_val(*ptep) & _PAGE_HASHPTE) - flush_hash_entry(mm, ptep, addr); -#endif - __asm__ __volatile__("\ - stw%U0%X0 %2,%0\n\ - eieio\n\ - stw%U0%X0 %L2,%1" - : "=m" (*ptep), "=m" (*((unsigned char *)ptep+4)) - : "r" (pte) : "memory"); - -#elif defined(CONFIG_PPC_STD_MMU_32) - /* Third case is 32-bit hash table in UP mode, we need to preserve - * the _PAGE_HASHPTE bit since we may not have invalidated the previous - * translation in the hash yet (done in a subsequent flush_tlb_xxx()) - * and see we need to keep track that this PTE needs invalidating - */ - *ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE) - | (pte_val(pte) & ~_PAGE_HASHPTE)); - -#else /* Anything else just stores the PTE normally. That covers all 64-bit * cases, and 32-bit non-hash with 32-bit PTEs. */ *ptep = pte; -#ifdef CONFIG_PPC_BOOK3E_64 /* * With hardware tablewalk, a sync is needed to ensure that * subsequent accesses see the PTE we just wrote. Unlike userspace * mappings, we can't tolerate spurious faults, so make sure * the new PTE will be seen the first time. */ - if (is_kernel_addr(addr)) + if (IS_ENABLED(CONFIG_PPC_BOOK3E_64) && is_kernel_addr(addr)) mb(); -#endif -#endif } diff --git a/arch/powerpc/include/asm/nohash/pte-book3e.h b/arch/powerpc/include/asm/nohash/pte-book3e.h index ccee8eb509bb..12730b81cd98 100644 --- a/arch/powerpc/include/asm/nohash/pte-book3e.h +++ b/arch/powerpc/include/asm/nohash/pte-book3e.h @@ -57,14 +57,8 @@ #define _PAGE_USER (_PAGE_BAP_UR | _PAGE_BAP_SR) /* Can be read */ #define _PAGE_PRIVILEGED (_PAGE_BAP_SR) -#define _PAGE_HASHPTE 0 -#define _PAGE_BUSY 0 - #define _PAGE_SPECIAL _PAGE_SW0 -/* Flags to be preserved on PTE modifications */ -#define _PAGE_HPTEFLAGS _PAGE_BUSY - /* Base page size */ #ifdef CONFIG_PPC_64K_PAGES #define _PAGE_PSIZE _PAGE_PSIZE_64K diff --git a/arch/powerpc/include/asm/opal-api.h b/arch/powerpc/include/asm/opal-api.h index d886a5b7ff21..f34d173a2ebf 100644 --- a/arch/powerpc/include/asm/opal-api.h +++ b/arch/powerpc/include/asm/opal-api.h @@ -204,6 +204,7 @@ #define OPAL_NPU_SPA_SETUP 159 #define OPAL_NPU_SPA_CLEAR_CACHE 160 #define OPAL_NPU_TL_SET 161 +#define OPAL_SENSOR_READ_U64 162 #define OPAL_PCI_GET_PBCQ_TUNNEL_BAR 164 #define OPAL_PCI_SET_PBCQ_TUNNEL_BAR 165 #define OPAL_LAST 165 diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index 03e1a920491e..3960def0e39c 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -201,6 +201,7 @@ int64_t opal_get_param(uint64_t token, uint32_t param_id, uint64_t buffer, int64_t opal_set_param(uint64_t token, uint32_t param_id, uint64_t buffer, uint64_t length); int64_t opal_sensor_read(uint32_t sensor_hndl, int token, __be32 *sensor_data); +int64_t opal_sensor_read_u64(u32 sensor_hndl, int token, __be64 *sensor_data); int64_t opal_handle_hmi(void); int64_t opal_register_dump_region(uint32_t id, uint64_t start, uint64_t end); int64_t opal_unregister_dump_region(uint32_t id); @@ -323,6 +324,7 @@ extern int opal_async_wait_response(uint64_t token, struct opal_msg *msg); extern int opal_async_wait_response_interruptible(uint64_t token, struct opal_msg *msg); extern int opal_get_sensor_data(u32 sensor_hndl, u32 *sensor_data); +extern int opal_get_sensor_data_u64(u32 sensor_hndl, u64 *sensor_data); struct rtc_time; extern unsigned long opal_get_boot_time(void); diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index 4185f1c96125..163f13f31255 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -223,6 +223,7 @@ struct paca_struct { u8 hmi_event_available; /* HMI event is available */ u8 hmi_p9_special_emu; /* HMI P9 special emulation */ #endif + u8 ftrace_enabled; /* Hard disable ftrace */ /* Stuff for accurate time accounting */ struct cpu_accounting_data accounting; diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h index dec9ce5ba8af..db7be0779d55 100644 --- a/arch/powerpc/include/asm/page.h +++ b/arch/powerpc/include/asm/page.h @@ -39,6 +39,7 @@ #ifndef __ASSEMBLY__ #ifdef CONFIG_HUGETLB_PAGE +extern bool hugetlb_disabled; extern unsigned int HPAGE_SHIFT; #else #define HPAGE_SHIFT PAGE_SHIFT diff --git a/arch/powerpc/include/asm/pmac_pfunc.h b/arch/powerpc/include/asm/pmac_pfunc.h index 73bd8f28f2a8..cee4e9f5b8cf 100644 --- a/arch/powerpc/include/asm/pmac_pfunc.h +++ b/arch/powerpc/include/asm/pmac_pfunc.h @@ -245,6 +245,7 @@ extern void pmf_put_function(struct pmf_function *func); extern int pmf_call_one(struct pmf_function *func, struct pmf_args *args); +int pmac_pfunc_base_install(void); /* Suspend/resume code called by via-pmu directly for now */ extern void pmac_pfunc_base_suspend(void); diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index 18883b8a6dac..4436887bc415 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -162,6 +162,7 @@ /* VMX Vector Store Instructions */ #define OP_31_XOP_STVX 231 +#define OP_31 31 #define OP_LWZ 32 #define OP_STFS 52 #define OP_STFSU 53 diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h index 13f7f4c0e1ea..75ece56dcd62 100644 --- a/arch/powerpc/include/asm/ppc_asm.h +++ b/arch/powerpc/include/asm/ppc_asm.h @@ -80,10 +80,8 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR) #else #define SAVE_GPR(n, base) stw n,GPR0+4*(n)(base) #define REST_GPR(n, base) lwz n,GPR0+4*(n)(base) -#define SAVE_NVGPRS(base) SAVE_GPR(13, base); SAVE_8GPRS(14, base); \ - SAVE_10GPRS(22, base) -#define REST_NVGPRS(base) REST_GPR(13, base); REST_8GPRS(14, base); \ - REST_10GPRS(22, base) +#define SAVE_NVGPRS(base) stmw 13, GPR0+4*13(base) +#define REST_NVGPRS(base) lmw 13, GPR0+4*13(base) #endif #define SAVE_2GPRS(n, base) SAVE_GPR(n, base); SAVE_GPR(n+1, base) diff --git a/arch/powerpc/include/asm/pte-common.h b/arch/powerpc/include/asm/pte-common.h index c4a72c7a8c83..050b0d775324 100644 --- a/arch/powerpc/include/asm/pte-common.h +++ b/arch/powerpc/include/asm/pte-common.h @@ -60,10 +60,6 @@ #ifndef _PMD_PRESENT_MASK #define _PMD_PRESENT_MASK _PMD_PRESENT #endif -#ifndef _PMD_SIZE -#define _PMD_SIZE 0 -#define PMD_PAGE_SIZE(pmd) bad_call_to_PMD_PAGE_SIZE() -#endif #ifndef _PMD_USER #define _PMD_USER 0 #endif @@ -88,11 +84,7 @@ #define _PTE_NONE_MASK _PAGE_HPTEFLAGS #endif -/* Make sure we get a link error if PMD_PAGE_SIZE is ever called on a - * kernel without large page PMD support - */ #ifndef __ASSEMBLY__ -extern unsigned long bad_call_to_PMD_PAGE_SIZE(void); /* * Don't just check for any non zero bits in __PAGE_USER, since for book3e diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index cb0f272ce123..75c5b2cd9d66 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -146,6 +146,12 @@ #define MSR_64BIT 0 #endif +/* Condition Register related */ +#define CR0_SHIFT 28 +#define CR0_MASK 0xF +#define CR0_TBEGIN_FAILURE (0x2 << 28) /* 0b0010 */ + + /* Power Management - Processor Stop Status and Control Register Fields */ #define PSSCR_RL_MASK 0x0000000F /* Requested Level */ #define PSSCR_MTL_MASK 0x000000F0 /* Maximum Transition Level */ @@ -239,13 +245,27 @@ #define SPRN_TFIAR 0x81 /* Transaction Failure Inst Addr */ #define SPRN_TEXASR 0x82 /* Transaction EXception & Summary */ #define SPRN_TEXASRU 0x83 /* '' '' '' Upper 32 */ -#define TEXASR_ABORT __MASK(63-31) /* terminated by tabort or treclaim */ -#define TEXASR_SUSP __MASK(63-32) /* tx failed in suspended state */ -#define TEXASR_HV __MASK(63-34) /* MSR[HV] when failure occurred */ -#define TEXASR_PR __MASK(63-35) /* MSR[PR] when failure occurred */ -#define TEXASR_FS __MASK(63-36) /* TEXASR Failure Summary */ -#define TEXASR_EXACT __MASK(63-37) /* TFIAR value is exact */ + +#define TEXASR_FC_LG (63 - 7) /* Failure Code */ +#define TEXASR_AB_LG (63 - 31) /* Abort */ +#define TEXASR_SU_LG (63 - 32) /* Suspend */ +#define TEXASR_HV_LG (63 - 34) /* Hypervisor state*/ +#define TEXASR_PR_LG (63 - 35) /* Privilege level */ +#define TEXASR_FS_LG (63 - 36) /* failure summary */ +#define TEXASR_EX_LG (63 - 37) /* TFIAR exact bit */ +#define TEXASR_ROT_LG (63 - 38) /* ROT bit */ + +#define TEXASR_ABORT __MASK(TEXASR_AB_LG) /* terminated by tabort or treclaim */ +#define TEXASR_SUSP __MASK(TEXASR_SU_LG) /* tx failed in suspended state */ +#define TEXASR_HV __MASK(TEXASR_HV_LG) /* MSR[HV] when failure occurred */ +#define TEXASR_PR __MASK(TEXASR_PR_LG) /* MSR[PR] when failure occurred */ +#define TEXASR_FS __MASK(TEXASR_FS_LG) /* TEXASR Failure Summary */ +#define TEXASR_EXACT __MASK(TEXASR_EX_LG) /* TFIAR value is exact */ +#define TEXASR_ROT __MASK(TEXASR_ROT_LG) +#define TEXASR_FC (ASM_CONST(0xFF) << TEXASR_FC_LG) + #define SPRN_TFHAR 0x80 /* Transaction Failure Handler Addr */ + #define SPRN_TIDR 144 /* Thread ID register */ #define SPRN_CTRLF 0x088 #define SPRN_CTRLT 0x098 diff --git a/arch/powerpc/include/asm/rheap.h b/arch/powerpc/include/asm/rheap.h index 172381769cfc..8e83703d6736 100644 --- a/arch/powerpc/include/asm/rheap.h +++ b/arch/powerpc/include/asm/rheap.h @@ -83,6 +83,9 @@ extern int rh_get_stats(rh_info_t * info, int what, int max_stats, /* Simple dump of remote heap info */ extern void rh_dump(rh_info_t * info); +/* Simple dump of remote info block */ +void rh_dump_blk(rh_info_t *info, rh_block_t *blk); + /* Set owner of taken block */ extern int rh_set_owner(rh_info_t * info, unsigned long start, const char *owner); diff --git a/arch/powerpc/include/asm/syscalls.h b/arch/powerpc/include/asm/syscalls.h index 1b90a3516a35..398171fdcd9f 100644 --- a/arch/powerpc/include/asm/syscalls.h +++ b/arch/powerpc/include/asm/syscalls.h @@ -16,7 +16,7 @@ asmlinkage long sys_mmap2(unsigned long addr, size_t len, unsigned long prot, unsigned long flags, unsigned long fd, unsigned long pgoff); asmlinkage long ppc64_personality(unsigned long personality); -asmlinkage int ppc_rtas(struct rtas_args __user *uargs); +asmlinkage long sys_rtas(struct rtas_args __user *uargs); #endif /* __KERNEL__ */ #endif /* __ASM_POWERPC_SYSCALLS_H */ diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h index d61f9c96d916..79a3b47e4839 100644 --- a/arch/powerpc/include/asm/systbl.h +++ b/arch/powerpc/include/asm/systbl.h @@ -147,7 +147,7 @@ SYSCALL_SPU(setfsuid) SYSCALL_SPU(setfsgid) SYSCALL_SPU(llseek) COMPAT_SYS_SPU(getdents) -SYSX_SPU(sys_select,ppc32_select,sys_select) +COMPAT_SPU_NEW(select) SYSCALL_SPU(flock) SYSCALL_SPU(msync) COMPAT_SYS_SPU(readv) @@ -245,7 +245,7 @@ SYSCALL_SPU(epoll_create) SYSCALL_SPU(epoll_ctl) SYSCALL_SPU(epoll_wait) SYSCALL_SPU(remap_file_pages) -SYSX_SPU(sys_timer_create,compat_sys_timer_create,sys_timer_create) +COMPAT_SYS_SPU(timer_create) COMPAT_SYS_SPU(timer_settime) COMPAT_SYS_SPU(timer_gettime) SYSCALL_SPU(timer_getoverrun) @@ -260,7 +260,7 @@ COMPAT_SYS_SPU(utimes) COMPAT_SYS_SPU(statfs64) COMPAT_SYS_SPU(fstatfs64) SYSX(sys_ni_syscall,ppc_fadvise64_64,ppc_fadvise64_64) -PPC_SYS_SPU(rtas) +SYSCALL_SPU(rtas) OLDSYS(debug_setcontext) SYSCALL(ni_syscall) COMPAT_SYS(migrate_pages) diff --git a/arch/powerpc/include/asm/tm.h b/arch/powerpc/include/asm/tm.h index b1658c97047c..e94f6db5e367 100644 --- a/arch/powerpc/include/asm/tm.h +++ b/arch/powerpc/include/asm/tm.h @@ -10,12 +10,10 @@ #ifndef __ASSEMBLY__ -extern void tm_enable(void); extern void tm_reclaim(struct thread_struct *thread, uint8_t cause); extern void tm_reclaim_current(uint8_t cause); extern void tm_recheckpoint(struct thread_struct *thread); -extern void tm_abort(uint8_t cause); extern void tm_save_sprs(struct thread_struct *thread); extern void tm_restore_sprs(struct thread_struct *thread); diff --git a/arch/powerpc/include/asm/trace.h b/arch/powerpc/include/asm/trace.h index 33f3b479138b..d018e8602694 100644 --- a/arch/powerpc/include/asm/trace.h +++ b/arch/powerpc/include/asm/trace.h @@ -81,8 +81,7 @@ TRACE_EVENT_FN_COND(hcall_entry, TRACE_EVENT_FN_COND(hcall_exit, - TP_PROTO(unsigned long opcode, unsigned long retval, - unsigned long *retbuf), + TP_PROTO(unsigned long opcode, long retval, unsigned long *retbuf), TP_ARGS(opcode, retval, retbuf), @@ -90,7 +89,7 @@ TRACE_EVENT_FN_COND(hcall_exit, TP_STRUCT__entry( __field(unsigned long, opcode) - __field(unsigned long, retval) + __field(long, retval) ), TP_fast_assign( @@ -98,7 +97,7 @@ TRACE_EVENT_FN_COND(hcall_exit, __entry->retval = retval; ), - TP_printk("opcode=%lu retval=%lu", __entry->opcode, __entry->retval), + TP_printk("opcode=%lu retval=%ld", __entry->opcode, __entry->retval), hcall_tracepoint_regfunc, hcall_tracepoint_unregfunc ); diff --git a/arch/powerpc/include/asm/xmon.h b/arch/powerpc/include/asm/xmon.h index eb42a0c6e1d9..30ff69bd8f43 100644 --- a/arch/powerpc/include/asm/xmon.h +++ b/arch/powerpc/include/asm/xmon.h @@ -29,7 +29,7 @@ static inline void xmon_register_spus(struct list_head *list) { }; extern int cpus_are_in_xmon(void); #endif -extern void xmon_printf(const char *format, ...); +extern __printf(1, 2) void xmon_printf(const char *format, ...); #endif /* __KERNEL __ */ #endif /* __ASM_POWERPC_XMON_H */ diff --git a/arch/powerpc/include/asm/xor.h b/arch/powerpc/include/asm/xor.h index a36c2069d8ed..7d6dc503349d 100644 --- a/arch/powerpc/include/asm/xor.h +++ b/arch/powerpc/include/asm/xor.h @@ -24,17 +24,7 @@ #include <asm/cputable.h> #include <asm/cpu_has_feature.h> - -void xor_altivec_2(unsigned long bytes, unsigned long *v1_in, - unsigned long *v2_in); -void xor_altivec_3(unsigned long bytes, unsigned long *v1_in, - unsigned long *v2_in, unsigned long *v3_in); -void xor_altivec_4(unsigned long bytes, unsigned long *v1_in, - unsigned long *v2_in, unsigned long *v3_in, - unsigned long *v4_in); -void xor_altivec_5(unsigned long bytes, unsigned long *v1_in, - unsigned long *v2_in, unsigned long *v3_in, - unsigned long *v4_in, unsigned long *v5_in); +#include <asm/xor_altivec.h> static struct xor_block_template xor_block_altivec = { .name = "altivec", diff --git a/arch/powerpc/include/asm/xor_altivec.h b/arch/powerpc/include/asm/xor_altivec.h new file mode 100644 index 000000000000..6ca923510b59 --- /dev/null +++ b/arch/powerpc/include/asm/xor_altivec.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_XOR_ALTIVEC_H +#define _ASM_POWERPC_XOR_ALTIVEC_H + +#ifdef CONFIG_ALTIVEC + +void xor_altivec_2(unsigned long bytes, unsigned long *v1_in, + unsigned long *v2_in); +void xor_altivec_3(unsigned long bytes, unsigned long *v1_in, + unsigned long *v2_in, unsigned long *v3_in); +void xor_altivec_4(unsigned long bytes, unsigned long *v1_in, + unsigned long *v2_in, unsigned long *v3_in, + unsigned long *v4_in); +void xor_altivec_5(unsigned long bytes, unsigned long *v1_in, + unsigned long *v2_in, unsigned long *v3_in, + unsigned long *v4_in, unsigned long *v5_in); + +#endif +#endif /* _ASM_POWERPC_XOR_ALTIVEC_H */ diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 6bee65f3cfd3..262c44a90ea1 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -180,6 +180,7 @@ int main(void) OFFSET(PACAKMSR, paca_struct, kernel_msr); OFFSET(PACAIRQSOFTMASK, paca_struct, irq_soft_mask); OFFSET(PACAIRQHAPPENED, paca_struct, irq_happened); + OFFSET(PACA_FTRACE_ENABLED, paca_struct, ftrace_enabled); #ifdef CONFIG_PPC_BOOK3S OFFSET(PACACONTEXTID, paca_struct, mm_ctx_id); #ifdef CONFIG_PPC_MM_SLICES diff --git a/arch/powerpc/kernel/btext.c b/arch/powerpc/kernel/btext.c index 6537cba1a758..b2072d5bbf2b 100644 --- a/arch/powerpc/kernel/btext.c +++ b/arch/powerpc/kernel/btext.c @@ -157,20 +157,20 @@ void btext_map(void) /* By default, we are no longer mapped */ boot_text_mapped = 0; - if (dispDeviceBase == 0) + if (!dispDeviceBase) return; base = ((unsigned long) dispDeviceBase) & 0xFFFFF000UL; offset = ((unsigned long) dispDeviceBase) - base; size = dispDeviceRowBytes * dispDeviceRect[3] + offset + dispDeviceRect[0]; vbase = __ioremap(base, size, pgprot_val(pgprot_noncached_wc(__pgprot(0)))); - if (vbase == 0) + if (!vbase) return; logicalDisplayBase = vbase + offset; boot_text_mapped = 1; } -int btext_initialize(struct device_node *np) +static int btext_initialize(struct device_node *np) { unsigned int width, height, depth, pitch; unsigned long address = 0; @@ -270,7 +270,7 @@ static unsigned char * calc_base(int x, int y) unsigned char *base; base = logicalDisplayBase; - if (base == 0) + if (!base) base = dispDeviceBase; base += (x + dispDeviceRect[0]) * (dispDeviceDepth >> 3); base += (y + dispDeviceRect[1]) * dispDeviceRowBytes; @@ -281,7 +281,7 @@ static unsigned char * calc_base(int x, int y) void btext_update_display(unsigned long phys, int width, int height, int depth, int pitch) { - if (dispDeviceBase == 0) + if (!dispDeviceBase) return; /* check it's the same frame buffer (within 256MB) */ diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index 3c2c2688918f..07e8396d472b 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -335,6 +335,26 @@ static unsigned long get_fadump_area_size(void) return size; } +static void __init fadump_reserve_crash_area(unsigned long base, + unsigned long size) +{ + struct memblock_region *reg; + unsigned long mstart, mend, msize; + + for_each_memblock(memory, reg) { + mstart = max_t(unsigned long, base, reg->base); + mend = reg->base + reg->size; + mend = min(base + size, mend); + + if (mstart < mend) { + msize = mend - mstart; + memblock_reserve(mstart, msize); + pr_info("Reserved %ldMB of memory at %#016lx for saving crash dump\n", + (msize >> 20), mstart); + } + } +} + int __init fadump_reserve_mem(void) { unsigned long base, size, memory_boundary; @@ -380,7 +400,16 @@ int __init fadump_reserve_mem(void) memory_boundary = memblock_end_of_DRAM(); if (fw_dump.dump_active) { - printk(KERN_INFO "Firmware-assisted dump is active.\n"); + pr_info("Firmware-assisted dump is active.\n"); + +#ifdef CONFIG_HUGETLB_PAGE + /* + * FADump capture kernel doesn't care much about hugepages. + * In fact, handling hugepages in capture kernel is asking for + * trouble. So, disable HugeTLB support when fadump is active. + */ + hugetlb_disabled = true; +#endif /* * If last boot has crashed then reserve all the memory * above boot_memory_size so that we don't touch it until @@ -389,11 +418,7 @@ int __init fadump_reserve_mem(void) */ base = fw_dump.boot_memory_size; size = memory_boundary - base; - memblock_reserve(base, size); - printk(KERN_INFO "Reserved %ldMB of memory at %ldMB " - "for saving crash dump\n", - (unsigned long)(size >> 20), - (unsigned long)(base >> 20)); + fadump_reserve_crash_area(base, size); fw_dump.fadumphdr_addr = be64_to_cpu(fdm_active->rmr_region.destination_address) + @@ -1155,6 +1180,9 @@ void fadump_cleanup(void) init_fadump_mem_struct(&fdm, be64_to_cpu(fdm_active->cpu_state_data.destination_address)); fadump_invalidate_dump(&fdm); + } else if (fw_dump.dump_registered) { + /* Un-register Firmware-assisted dump if it was registered. */ + fadump_unregister_dump(&fdm); } } diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index d8670a37d70c..6cab07e76732 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -913,7 +913,7 @@ start_here: tovirt(r6,r6) lis r5, abatron_pteptrs@h ori r5, r5, abatron_pteptrs@l - stw r5, 0xf0(r0) /* Must match your Abatron config file */ + stw r5, 0xf0(0) /* Must match your Abatron config file */ tophys(r5,r5) stw r6, 0(r5) diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index 4c1012b80d3b..80547dad37da 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -178,8 +178,8 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) if (cpu_has_feature(CPU_FTR_DAWR)) { length_max = 512 ; /* 64 doublewords */ /* DAWR region can't cross 512 boundary */ - if ((bp->attr.bp_addr >> 10) != - ((bp->attr.bp_addr + bp->attr.bp_len - 1) >> 10)) + if ((bp->attr.bp_addr >> 9) != + ((bp->attr.bp_addr + bp->attr.bp_len - 1) >> 9)) return -EINVAL; } if (info->len > diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 061aa0f47bb1..bbf7ec582d60 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -89,7 +89,7 @@ atomic_t ppc_n_lost_interrupts; #ifdef CONFIG_TAU_INT extern int tau_initialized; -extern int tau_interrupts(int); +u32 tau_interrupts(unsigned long cpu); #endif #endif /* CONFIG_PPC32 */ diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c index 9ad37f827a97..683b5b3805bd 100644 --- a/arch/powerpc/kernel/kvm.c +++ b/arch/powerpc/kernel/kvm.c @@ -25,6 +25,7 @@ #include <linux/kvm_para.h> #include <linux/slab.h> #include <linux/of.h> +#include <linux/pagemap.h> #include <asm/reg.h> #include <asm/sections.h> @@ -672,14 +673,13 @@ static void kvm_use_magic_page(void) { u32 *p; u32 *start, *end; - u32 tmp; u32 features; /* Tell the host to map the magic page to -4096 on all CPUs */ on_each_cpu(kvm_map_magic_page, &features, 1); /* Quick self-test to see if the mapping works */ - if (__get_user(tmp, (u32*)KVM_MAGIC_PAGE)) { + if (!fault_in_pages_readable((const char *)KVM_MAGIC_PAGE, sizeof(u32))) { kvm_patching_worked = false; return; } diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c index 2694d078741d..936c7e2d421e 100644 --- a/arch/powerpc/kernel/machine_kexec.c +++ b/arch/powerpc/kernel/machine_kexec.c @@ -98,12 +98,14 @@ void machine_kexec(struct kimage *image) int save_ftrace_enabled; save_ftrace_enabled = __ftrace_enabled_save(); + this_cpu_disable_ftrace(); if (ppc_md.machine_kexec) ppc_md.machine_kexec(image); else default_machine_kexec(image); + this_cpu_enable_ftrace(); __ftrace_enabled_restore(save_ftrace_enabled); /* Fall back to normal restart if we're still alive. */ diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c index 1044bf15d5ed..a0f6f45005bd 100644 --- a/arch/powerpc/kernel/machine_kexec_64.c +++ b/arch/powerpc/kernel/machine_kexec_64.c @@ -231,16 +231,16 @@ static void kexec_prepare_cpus(void) /* we are sure every CPU has IRQs off at this point */ kexec_all_irq_disabled = 1; - /* after we tell the others to go down */ - if (ppc_md.kexec_cpu_down) - ppc_md.kexec_cpu_down(0, 0); - /* * Before removing MMU mappings make sure all CPUs have entered real * mode: */ kexec_prepare_cpus_wait(KEXEC_STATE_REAL_MODE); + /* after we tell the others to go down */ + if (ppc_md.kexec_cpu_down) + ppc_md.kexec_cpu_down(0, 0); + put_cpu(); } diff --git a/arch/powerpc/kernel/misc.S b/arch/powerpc/kernel/misc.S index 384357cb8bc0..2f18fc1368d0 100644 --- a/arch/powerpc/kernel/misc.S +++ b/arch/powerpc/kernel/misc.S @@ -60,6 +60,10 @@ _GLOBAL(setjmp) PPC_STL r0,0(r3) PPC_STL r1,SZL(r3) PPC_STL r2,2*SZL(r3) +#ifdef CONFIG_PPC32 + mfcr r12 + stmw r12, 3*SZL(r3) +#else mfcr r0 PPC_STL r0,3*SZL(r3) PPC_STL r13,4*SZL(r3) @@ -81,14 +85,16 @@ _GLOBAL(setjmp) PPC_STL r29,20*SZL(r3) PPC_STL r30,21*SZL(r3) PPC_STL r31,22*SZL(r3) +#endif li r3,0 blr _GLOBAL(longjmp) - PPC_LCMPI r4,0 - bne 1f - li r4,1 -1: PPC_LL r13,4*SZL(r3) +#ifdef CONFIG_PPC32 + lmw r12, 3*SZL(r3) + mtcrf 0x38, r12 +#else + PPC_LL r13,4*SZL(r3) PPC_LL r14,5*SZL(r3) PPC_LL r15,6*SZL(r3) PPC_LL r16,7*SZL(r3) @@ -109,11 +115,14 @@ _GLOBAL(longjmp) PPC_LL r31,22*SZL(r3) PPC_LL r0,3*SZL(r3) mtcrf 0x38,r0 +#endif PPC_LL r0,0(r3) PPC_LL r1,SZL(r3) PPC_LL r2,2*SZL(r3) mtlr r0 - mr r3,r4 + mr. r3, r4 + bnelr + li r3, 1 blr _GLOBAL(current_stack_pointer) diff --git a/arch/powerpc/kernel/module_32.c b/arch/powerpc/kernel/module_32.c index 5a7a78f12562..88d83771f462 100644 --- a/arch/powerpc/kernel/module_32.c +++ b/arch/powerpc/kernel/module_32.c @@ -109,12 +109,12 @@ static unsigned long get_plt_size(const Elf32_Ehdr *hdr, for (i = 1; i < hdr->e_shnum; i++) { /* If it's called *.init*, and we're not init, we're not interested */ - if ((strstr(secstrings + sechdrs[i].sh_name, ".init") != 0) + if ((strstr(secstrings + sechdrs[i].sh_name, ".init") != NULL) != is_init) continue; /* We don't want to look at debug sections. */ - if (strstr(secstrings + sechdrs[i].sh_name, ".debug") != 0) + if (strstr(secstrings + sechdrs[i].sh_name, ".debug")) continue; if (sechdrs[i].sh_type == SHT_RELA) { diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index a2636c250b7b..1b7419579820 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -280,6 +280,10 @@ static unsigned long get_stubs_size(const Elf64_Ehdr *hdr, #ifdef CONFIG_DYNAMIC_FTRACE /* make the trampoline to the ftrace_caller */ relocs++; +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS + /* an additional one for ftrace_regs_caller */ + relocs++; +#endif #endif pr_debug("Looks like a total of %lu stubs, max\n", relocs); @@ -463,8 +467,11 @@ static unsigned long stub_for_addr(const Elf64_Shdr *sechdrs, } #ifdef CC_USING_MPROFILE_KERNEL -static bool is_early_mcount_callsite(u32 *instruction) +static bool is_mprofile_mcount_callsite(const char *name, u32 *instruction) { + if (strcmp("_mcount", name)) + return false; + /* * Check if this is one of the -mprofile-kernel sequences. */ @@ -496,8 +503,7 @@ static void squash_toc_save_inst(const char *name, unsigned long addr) #else static void squash_toc_save_inst(const char *name, unsigned long addr) { } -/* without -mprofile-kernel, mcount calls are never early */ -static bool is_early_mcount_callsite(u32 *instruction) +static bool is_mprofile_mcount_callsite(const char *name, u32 *instruction) { return false; } @@ -505,11 +511,11 @@ static bool is_early_mcount_callsite(u32 *instruction) /* We expect a noop next: if it is, replace it with instruction to restore r2. */ -static int restore_r2(u32 *instruction, struct module *me) +static int restore_r2(const char *name, u32 *instruction, struct module *me) { u32 *prev_insn = instruction - 1; - if (is_early_mcount_callsite(prev_insn)) + if (is_mprofile_mcount_callsite(name, prev_insn)) return 1; /* @@ -650,7 +656,8 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, value = stub_for_addr(sechdrs, value, me); if (!value) return -ENOENT; - if (!restore_r2((u32 *)location + 1, me)) + if (!restore_r2(strtab + sym->st_name, + (u32 *)location + 1, me)) return -ENOEXEC; squash_toc_save_inst(strtab + sym->st_name, value); @@ -762,7 +769,8 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, * via the paca (in r13). The target (ftrace_caller()) is responsible for * saving and restoring the toc before returning. */ -static unsigned long create_ftrace_stub(const Elf64_Shdr *sechdrs, struct module *me) +static unsigned long create_ftrace_stub(const Elf64_Shdr *sechdrs, + struct module *me, unsigned long addr) { struct ppc64_stub_entry *entry; unsigned int i, num_stubs; @@ -789,9 +797,10 @@ static unsigned long create_ftrace_stub(const Elf64_Shdr *sechdrs, struct module memcpy(entry->jump, stub_insns, sizeof(stub_insns)); /* Stub uses address relative to kernel toc (from the paca) */ - reladdr = (unsigned long)ftrace_caller - kernel_toc_addr(); + reladdr = addr - kernel_toc_addr(); if (reladdr > 0x7FFFFFFF || reladdr < -(0x80000000L)) { - pr_err("%s: Address of ftrace_caller out of range of kernel_toc.\n", me->name); + pr_err("%s: Address of %ps out of range of kernel_toc.\n", + me->name, (void *)addr); return 0; } @@ -799,22 +808,29 @@ static unsigned long create_ftrace_stub(const Elf64_Shdr *sechdrs, struct module entry->jump[2] |= PPC_LO(reladdr); /* Eventhough we don't use funcdata in the stub, it's needed elsewhere. */ - entry->funcdata = func_desc((unsigned long)ftrace_caller); + entry->funcdata = func_desc(addr); entry->magic = STUB_MAGIC; return (unsigned long)entry; } #else -static unsigned long create_ftrace_stub(const Elf64_Shdr *sechdrs, struct module *me) +static unsigned long create_ftrace_stub(const Elf64_Shdr *sechdrs, + struct module *me, unsigned long addr) { - return stub_for_addr(sechdrs, (unsigned long)ftrace_caller, me); + return stub_for_addr(sechdrs, addr, me); } #endif int module_finalize_ftrace(struct module *mod, const Elf_Shdr *sechdrs) { - mod->arch.toc = my_r2(sechdrs, mod); - mod->arch.tramp = create_ftrace_stub(sechdrs, mod); + mod->arch.tramp = create_ftrace_stub(sechdrs, mod, + (unsigned long)ftrace_caller); +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS + mod->arch.tramp_regs = create_ftrace_stub(sechdrs, mod, + (unsigned long)ftrace_regs_caller); + if (!mod->arch.tramp_regs) + return -ENOENT; +#endif if (!mod->arch.tramp) return -ENOENT; diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c index 85ad2f78b889..d63b488d34d7 100644 --- a/arch/powerpc/kernel/pci_32.c +++ b/arch/powerpc/kernel/pci_32.c @@ -11,11 +11,13 @@ #include <linux/sched.h> #include <linux/errno.h> #include <linux/bootmem.h> +#include <linux/syscalls.h> #include <linux/irq.h> #include <linux/list.h> #include <linux/of.h> #include <linux/slab.h> #include <linux/export.h> +#include <linux/syscalls.h> #include <asm/processor.h> #include <asm/io.h> @@ -283,7 +285,8 @@ pci_bus_to_hose(int bus) * Note that the returned IO or memory base is a physical address */ -long sys_pciconfig_iobase(long which, unsigned long bus, unsigned long devfn) +SYSCALL_DEFINE3(pciconfig_iobase, long, which, + unsigned long, bus, unsigned long, devfn) { struct pci_controller* hose; long result = -EOPNOTSUPP; @@ -307,5 +310,3 @@ long sys_pciconfig_iobase(long which, unsigned long bus, unsigned long devfn) return result; } - - diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c index 15ce0306b092..dff28f903512 100644 --- a/arch/powerpc/kernel/pci_64.c +++ b/arch/powerpc/kernel/pci_64.c @@ -203,8 +203,8 @@ void pcibios_setup_phb_io_space(struct pci_controller *hose) #define IOBASE_ISA_IO 3 #define IOBASE_ISA_MEM 4 -long sys_pciconfig_iobase(long which, unsigned long in_bus, - unsigned long in_devfn) +SYSCALL_DEFINE3(pciconfig_iobase, long, which, unsigned long, in_bus, + unsigned long, in_devfn) { struct pci_controller* hose; struct pci_bus *tmp_bus, *bus = NULL; diff --git a/arch/powerpc/kernel/ppc_save_regs.S b/arch/powerpc/kernel/ppc_save_regs.S index 1b1787d52896..8afbe213d729 100644 --- a/arch/powerpc/kernel/ppc_save_regs.S +++ b/arch/powerpc/kernel/ppc_save_regs.S @@ -25,6 +25,9 @@ */ _GLOBAL(ppc_save_regs) PPC_STL r0,0*SZL(r3) +#ifdef CONFIG_PPC32 + stmw r2, 2*SZL(r3) +#else PPC_STL r2,2*SZL(r3) PPC_STL r3,3*SZL(r3) PPC_STL r4,4*SZL(r3) @@ -55,6 +58,7 @@ _GLOBAL(ppc_save_regs) PPC_STL r29,29*SZL(r3) PPC_STL r30,30*SZL(r3) PPC_STL r31,31*SZL(r3) +#endif /* go up one stack frame for SP */ PPC_LL r4,0(r1) PPC_STL r4,1*SZL(r3) diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 1237f13fed51..25db000fa5b3 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -154,6 +154,7 @@ unsigned long msr_check_and_set(unsigned long bits) return newmsr; } +EXPORT_SYMBOL_GPL(msr_check_and_set); void __msr_check_and_clear(unsigned long bits) { diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 9dbed488aba1..05e7fb47a7a4 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -332,25 +332,10 @@ static int __init early_init_dt_scan_cpus(unsigned long node, * NOTE: This must match the parsing done in smp_setup_cpu_maps. */ for (i = 0; i < nthreads; i++) { - /* - * version 2 of the kexec param format adds the phys cpuid of - * booted proc. - */ - if (fdt_version(initial_boot_params) >= 2) { - if (be32_to_cpu(intserv[i]) == - fdt_boot_cpuid_phys(initial_boot_params)) { - found = boot_cpu_count; - found_thread = i; - } - } else { - /* - * Check if it's the boot-cpu, set it's hw index now, - * unfortunately this format did not support booting - * off secondary threads. - */ - if (of_get_flat_dt_prop(node, - "linux,boot-cpu", NULL) != NULL) - found = boot_cpu_count; + if (be32_to_cpu(intserv[i]) == + fdt_boot_cpuid_phys(initial_boot_params)) { + found = boot_cpu_count; + found_thread = i; } #ifdef CONFIG_SMP /* logical cpu id is always 0 on UP kernels */ diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index f9d6befb55a6..5425dd3d6a9f 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -103,7 +103,7 @@ int of_workarounds; #ifdef DEBUG_PROM #define prom_debug(x...) prom_printf(x) #else -#define prom_debug(x...) +#define prom_debug(x...) do { } while (0) #endif @@ -301,6 +301,10 @@ static void __init prom_print(const char *msg) } +/* + * Both prom_print_hex & prom_print_dec takes an unsigned long as input so that + * we do not need __udivdi3 or __umoddi3 on 32bits. + */ static void __init prom_print_hex(unsigned long val) { int i, nibbles = sizeof(val)*2; @@ -334,12 +338,14 @@ static void __init prom_print_dec(unsigned long val) call_prom("write", 3, 1, prom.stdout, buf+i, size); } +__printf(1, 2) static void __init prom_printf(const char *format, ...) { const char *p, *q, *s; va_list args; unsigned long v; long vs; + int n = 0; va_start(args, format); for (p = format; *p != 0; p = q) { @@ -358,6 +364,10 @@ static void __init prom_printf(const char *format, ...) ++q; if (*q == 0) break; + while (*q == 'l') { + ++q; + ++n; + } switch (*q) { case 's': ++q; @@ -366,39 +376,55 @@ static void __init prom_printf(const char *format, ...) break; case 'x': ++q; - v = va_arg(args, unsigned long); + switch (n) { + case 0: + v = va_arg(args, unsigned int); + break; + case 1: + v = va_arg(args, unsigned long); + break; + case 2: + default: + v = va_arg(args, unsigned long long); + break; + } prom_print_hex(v); break; - case 'd': + case 'u': ++q; - vs = va_arg(args, int); - if (vs < 0) { - prom_print("-"); - vs = -vs; + switch (n) { + case 0: + v = va_arg(args, unsigned int); + break; + case 1: + v = va_arg(args, unsigned long); + break; + case 2: + default: + v = va_arg(args, unsigned long long); + break; } - prom_print_dec(vs); + prom_print_dec(v); break; - case 'l': + case 'd': ++q; - if (*q == 0) + switch (n) { + case 0: + vs = va_arg(args, int); break; - else if (*q == 'x') { - ++q; - v = va_arg(args, unsigned long); - prom_print_hex(v); - } else if (*q == 'u') { /* '%lu' */ - ++q; - v = va_arg(args, unsigned long); - prom_print_dec(v); - } else if (*q == 'd') { /* %ld */ - ++q; + case 1: vs = va_arg(args, long); - if (vs < 0) { - prom_print("-"); - vs = -vs; - } - prom_print_dec(vs); + break; + case 2: + default: + vs = va_arg(args, long long); + break; } + if (vs < 0) { + prom_print("-"); + vs = -vs; + } + prom_print_dec(vs); break; } } @@ -1160,7 +1186,7 @@ static void __init prom_send_capabilities(void) */ cores = DIV_ROUND_UP(NR_CPUS, prom_count_smt_threads()); - prom_printf("Max number of cores passed to firmware: %lu (NR_CPUS = %lu)\n", + prom_printf("Max number of cores passed to firmware: %u (NR_CPUS = %d)\n", cores, NR_CPUS); ibm_architecture_vec.vec5.max_cpus = cpu_to_be32(cores); @@ -1242,7 +1268,7 @@ static unsigned long __init alloc_up(unsigned long size, unsigned long align) if (align) base = _ALIGN_UP(base, align); - prom_debug("alloc_up(%x, %x)\n", size, align); + prom_debug("%s(%lx, %lx)\n", __func__, size, align); if (ram_top == 0) prom_panic("alloc_up() called with mem not initialized\n"); @@ -1253,7 +1279,7 @@ static unsigned long __init alloc_up(unsigned long size, unsigned long align) for(; (base + size) <= alloc_top; base = _ALIGN_UP(base + 0x100000, align)) { - prom_debug(" trying: 0x%x\n\r", base); + prom_debug(" trying: 0x%lx\n\r", base); addr = (unsigned long)prom_claim(base, size, 0); if (addr != PROM_ERROR && addr != 0) break; @@ -1265,12 +1291,12 @@ static unsigned long __init alloc_up(unsigned long size, unsigned long align) return 0; alloc_bottom = addr + size; - prom_debug(" -> %x\n", addr); - prom_debug(" alloc_bottom : %x\n", alloc_bottom); - prom_debug(" alloc_top : %x\n", alloc_top); - prom_debug(" alloc_top_hi : %x\n", alloc_top_high); - prom_debug(" rmo_top : %x\n", rmo_top); - prom_debug(" ram_top : %x\n", ram_top); + prom_debug(" -> %lx\n", addr); + prom_debug(" alloc_bottom : %lx\n", alloc_bottom); + prom_debug(" alloc_top : %lx\n", alloc_top); + prom_debug(" alloc_top_hi : %lx\n", alloc_top_high); + prom_debug(" rmo_top : %lx\n", rmo_top); + prom_debug(" ram_top : %lx\n", ram_top); return addr; } @@ -1285,7 +1311,7 @@ static unsigned long __init alloc_down(unsigned long size, unsigned long align, { unsigned long base, addr = 0; - prom_debug("alloc_down(%x, %x, %s)\n", size, align, + prom_debug("%s(%lx, %lx, %s)\n", __func__, size, align, highmem ? "(high)" : "(low)"); if (ram_top == 0) prom_panic("alloc_down() called with mem not initialized\n"); @@ -1313,7 +1339,7 @@ static unsigned long __init alloc_down(unsigned long size, unsigned long align, base = _ALIGN_DOWN(alloc_top - size, align); for (; base > alloc_bottom; base = _ALIGN_DOWN(base - 0x100000, align)) { - prom_debug(" trying: 0x%x\n\r", base); + prom_debug(" trying: 0x%lx\n\r", base); addr = (unsigned long)prom_claim(base, size, 0); if (addr != PROM_ERROR && addr != 0) break; @@ -1324,12 +1350,12 @@ static unsigned long __init alloc_down(unsigned long size, unsigned long align, alloc_top = addr; bail: - prom_debug(" -> %x\n", addr); - prom_debug(" alloc_bottom : %x\n", alloc_bottom); - prom_debug(" alloc_top : %x\n", alloc_top); - prom_debug(" alloc_top_hi : %x\n", alloc_top_high); - prom_debug(" rmo_top : %x\n", rmo_top); - prom_debug(" ram_top : %x\n", ram_top); + prom_debug(" -> %lx\n", addr); + prom_debug(" alloc_bottom : %lx\n", alloc_bottom); + prom_debug(" alloc_top : %lx\n", alloc_top); + prom_debug(" alloc_top_hi : %lx\n", alloc_top_high); + prom_debug(" rmo_top : %lx\n", rmo_top); + prom_debug(" ram_top : %lx\n", ram_top); return addr; } @@ -1455,7 +1481,7 @@ static void __init prom_init_mem(void) if (size == 0) continue; - prom_debug(" %x %x\n", base, size); + prom_debug(" %lx %lx\n", base, size); if (base == 0 && (of_platform & PLATFORM_LPAR)) rmo_top = size; if ((base + size) > ram_top) @@ -1475,12 +1501,12 @@ static void __init prom_init_mem(void) if (prom_memory_limit) { if (prom_memory_limit <= alloc_bottom) { - prom_printf("Ignoring mem=%x <= alloc_bottom.\n", - prom_memory_limit); + prom_printf("Ignoring mem=%lx <= alloc_bottom.\n", + prom_memory_limit); prom_memory_limit = 0; } else if (prom_memory_limit >= ram_top) { - prom_printf("Ignoring mem=%x >= ram_top.\n", - prom_memory_limit); + prom_printf("Ignoring mem=%lx >= ram_top.\n", + prom_memory_limit); prom_memory_limit = 0; } else { ram_top = prom_memory_limit; @@ -1512,12 +1538,13 @@ static void __init prom_init_mem(void) alloc_bottom = PAGE_ALIGN(prom_initrd_end); prom_printf("memory layout at init:\n"); - prom_printf(" memory_limit : %x (16 MB aligned)\n", prom_memory_limit); - prom_printf(" alloc_bottom : %x\n", alloc_bottom); - prom_printf(" alloc_top : %x\n", alloc_top); - prom_printf(" alloc_top_hi : %x\n", alloc_top_high); - prom_printf(" rmo_top : %x\n", rmo_top); - prom_printf(" ram_top : %x\n", ram_top); + prom_printf(" memory_limit : %lx (16 MB aligned)\n", + prom_memory_limit); + prom_printf(" alloc_bottom : %lx\n", alloc_bottom); + prom_printf(" alloc_top : %lx\n", alloc_top); + prom_printf(" alloc_top_hi : %lx\n", alloc_top_high); + prom_printf(" rmo_top : %lx\n", rmo_top); + prom_printf(" ram_top : %lx\n", ram_top); } static void __init prom_close_stdin(void) @@ -1578,7 +1605,7 @@ static void __init prom_instantiate_opal(void) return; } - prom_printf("instantiating opal at 0x%x...", base); + prom_printf("instantiating opal at 0x%llx...", base); if (call_prom_ret("call-method", 4, 3, rets, ADDR("load-opal-runtime"), @@ -1594,10 +1621,10 @@ static void __init prom_instantiate_opal(void) reserve_mem(base, size); - prom_debug("opal base = 0x%x\n", base); - prom_debug("opal align = 0x%x\n", align); - prom_debug("opal entry = 0x%x\n", entry); - prom_debug("opal size = 0x%x\n", (long)size); + prom_debug("opal base = 0x%llx\n", base); + prom_debug("opal align = 0x%llx\n", align); + prom_debug("opal entry = 0x%llx\n", entry); + prom_debug("opal size = 0x%llx\n", size); prom_setprop(opal_node, "/ibm,opal", "opal-base-address", &base, sizeof(base)); @@ -1674,7 +1701,7 @@ static void __init prom_instantiate_rtas(void) prom_debug("rtas base = 0x%x\n", base); prom_debug("rtas entry = 0x%x\n", entry); - prom_debug("rtas size = 0x%x\n", (long)size); + prom_debug("rtas size = 0x%x\n", size); prom_debug("prom_instantiate_rtas: end...\n"); } @@ -1732,7 +1759,7 @@ static void __init prom_instantiate_sml(void) if (base == 0) prom_panic("Could not allocate memory for sml\n"); - prom_printf("instantiating sml at 0x%x...", base); + prom_printf("instantiating sml at 0x%llx...", base); memset((void *)base, 0, size); @@ -1751,8 +1778,8 @@ static void __init prom_instantiate_sml(void) prom_setprop(ibmvtpm_node, "/vdevice/vtpm", "linux,sml-size", &size, sizeof(size)); - prom_debug("sml base = 0x%x\n", base); - prom_debug("sml size = 0x%x\n", (long)size); + prom_debug("sml base = 0x%llx\n", base); + prom_debug("sml size = 0x%x\n", size); prom_debug("prom_instantiate_sml: end...\n"); } @@ -1845,7 +1872,7 @@ static void __init prom_initialize_tce_table(void) prom_debug("TCE table: %s\n", path); prom_debug("\tnode = 0x%x\n", node); - prom_debug("\tbase = 0x%x\n", base); + prom_debug("\tbase = 0x%llx\n", base); prom_debug("\tsize = 0x%x\n", minsize); /* Initialize the table to have a one-to-one mapping @@ -1932,12 +1959,12 @@ static void __init prom_hold_cpus(void) } prom_debug("prom_hold_cpus: start...\n"); - prom_debug(" 1) spinloop = 0x%x\n", (unsigned long)spinloop); - prom_debug(" 1) *spinloop = 0x%x\n", *spinloop); - prom_debug(" 1) acknowledge = 0x%x\n", + prom_debug(" 1) spinloop = 0x%lx\n", (unsigned long)spinloop); + prom_debug(" 1) *spinloop = 0x%lx\n", *spinloop); + prom_debug(" 1) acknowledge = 0x%lx\n", (unsigned long)acknowledge); - prom_debug(" 1) *acknowledge = 0x%x\n", *acknowledge); - prom_debug(" 1) secondary_hold = 0x%x\n", secondary_hold); + prom_debug(" 1) *acknowledge = 0x%lx\n", *acknowledge); + prom_debug(" 1) secondary_hold = 0x%lx\n", secondary_hold); /* Set the common spinloop variable, so all of the secondary cpus * will block when they are awakened from their OF spinloop. @@ -1965,7 +1992,7 @@ static void __init prom_hold_cpus(void) prom_getprop(node, "reg", ®, sizeof(reg)); cpu_no = be32_to_cpu(reg); - prom_debug("cpu hw idx = %lu\n", cpu_no); + prom_debug("cpu hw idx = %u\n", cpu_no); /* Init the acknowledge var which will be reset by * the secondary cpu when it awakens from its OF @@ -1975,7 +2002,7 @@ static void __init prom_hold_cpus(void) if (cpu_no != prom.cpu) { /* Primary Thread of non-boot cpu or any thread */ - prom_printf("starting cpu hw idx %lu... ", cpu_no); + prom_printf("starting cpu hw idx %u... ", cpu_no); call_prom("start-cpu", 3, 0, node, secondary_hold, cpu_no); @@ -1986,11 +2013,11 @@ static void __init prom_hold_cpus(void) if (*acknowledge == cpu_no) prom_printf("done\n"); else - prom_printf("failed: %x\n", *acknowledge); + prom_printf("failed: %lx\n", *acknowledge); } #ifdef CONFIG_SMP else - prom_printf("boot cpu hw idx %lu\n", cpu_no); + prom_printf("boot cpu hw idx %u\n", cpu_no); #endif /* CONFIG_SMP */ } @@ -2268,7 +2295,7 @@ static void __init *make_room(unsigned long *mem_start, unsigned long *mem_end, while ((*mem_start + needed) > *mem_end) { unsigned long room, chunk; - prom_debug("Chunk exhausted, claiming more at %x...\n", + prom_debug("Chunk exhausted, claiming more at %lx...\n", alloc_bottom); room = alloc_top - alloc_bottom; if (room > DEVTREE_CHUNK_SIZE) @@ -2494,7 +2521,7 @@ static void __init flatten_device_tree(void) room = alloc_top - alloc_bottom - 0x4000; if (room > DEVTREE_CHUNK_SIZE) room = DEVTREE_CHUNK_SIZE; - prom_debug("starting device tree allocs at %x\n", alloc_bottom); + prom_debug("starting device tree allocs at %lx\n", alloc_bottom); /* Now try to claim that */ mem_start = (unsigned long)alloc_up(room, PAGE_SIZE); @@ -2557,7 +2584,7 @@ static void __init flatten_device_tree(void) int i; prom_printf("reserved memory map:\n"); for (i = 0; i < mem_reserve_cnt; i++) - prom_printf(" %x - %x\n", + prom_printf(" %llx - %llx\n", be64_to_cpu(mem_reserve_map[i].base), be64_to_cpu(mem_reserve_map[i].size)); } @@ -2567,9 +2594,9 @@ static void __init flatten_device_tree(void) */ mem_reserve_cnt = MEM_RESERVE_MAP_SIZE; - prom_printf("Device tree strings 0x%x -> 0x%x\n", + prom_printf("Device tree strings 0x%lx -> 0x%lx\n", dt_string_start, dt_string_end); - prom_printf("Device tree struct 0x%x -> 0x%x\n", + prom_printf("Device tree struct 0x%lx -> 0x%lx\n", dt_struct_start, dt_struct_end); } @@ -3001,7 +3028,7 @@ static void __init prom_find_boot_cpu(void) prom_getprop(cpu_pkg, "reg", &rval, sizeof(rval)); prom.cpu = be32_to_cpu(rval); - prom_debug("Booting CPU hw index = %lu\n", prom.cpu); + prom_debug("Booting CPU hw index = %d\n", prom.cpu); } static void __init prom_check_initrd(unsigned long r3, unsigned long r4) @@ -3023,8 +3050,8 @@ static void __init prom_check_initrd(unsigned long r3, unsigned long r4) reserve_mem(prom_initrd_start, prom_initrd_end - prom_initrd_start); - prom_debug("initrd_start=0x%x\n", prom_initrd_start); - prom_debug("initrd_end=0x%x\n", prom_initrd_end); + prom_debug("initrd_start=0x%lx\n", prom_initrd_start); + prom_debug("initrd_end=0x%lx\n", prom_initrd_end); } #endif /* CONFIG_BLK_DEV_INITRD */ } @@ -3277,7 +3304,7 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4, /* Don't print anything after quiesce under OPAL, it crashes OFW */ if (of_platform != PLATFORM_OPAL) { prom_printf("Booting Linux via __start() @ 0x%lx ...\n", kbase); - prom_debug("->dt_header_start=0x%x\n", hdr); + prom_debug("->dt_header_start=0x%lx\n", hdr); } #ifdef CONFIG_PPC32 diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index d23cf632edf0..0f63dd5972e9 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -2443,6 +2443,7 @@ static int ptrace_set_debugreg(struct task_struct *task, unsigned long addr, /* Create a new breakpoint request if one doesn't exist already */ hw_breakpoint_init(&attr); attr.bp_addr = hw_brk.address; + attr.bp_len = 8; arch_bp_generic_fields(hw_brk.type, &attr.bp_type); diff --git a/arch/powerpc/kernel/rtas-proc.c b/arch/powerpc/kernel/rtas-proc.c index fb070d8cad07..11ef978e95db 100644 --- a/arch/powerpc/kernel/rtas-proc.c +++ b/arch/powerpc/kernel/rtas-proc.c @@ -528,7 +528,7 @@ static void ppc_rtas_process_sensor(struct seq_file *m, "EPOW power off" }; const char * battery_cyclestate[] = { "None", "In progress", "Requested" }; - const char * battery_charging[] = { "Charging", "Discharching", + const char * battery_charging[] = { "Charging", "Discharging", "No current flow" }; const char * ibm_drconnector[] = { "Empty", "Present", "Unusable", "Exchange" }; diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 3f1c4fcbe0aa..8afd146bc9c7 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -26,6 +26,7 @@ #include <linux/memblock.h> #include <linux/slab.h> #include <linux/reboot.h> +#include <linux/syscalls.h> #include <asm/prom.h> #include <asm/rtas.h> @@ -1050,7 +1051,7 @@ struct pseries_errorlog *get_pseries_errorlog(struct rtas_error_log *log, } /* We assume to be passed big endian arguments */ -asmlinkage int ppc_rtas(struct rtas_args __user *uargs) +SYSCALL_DEFINE1(rtas, struct rtas_args __user *, uargs) { struct rtas_args args; unsigned long flags; diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 0af5c11b9e78..62b1a40d8957 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -192,12 +192,6 @@ void machine_halt(void) machine_hang(); } - -#ifdef CONFIG_TAU -extern u32 cpu_temp(unsigned long cpu); -extern u32 cpu_temp_both(unsigned long cpu); -#endif /* CONFIG_TAU */ - #ifdef CONFIG_SMP DEFINE_PER_CPU(unsigned int, cpu_pvr); #endif diff --git a/arch/powerpc/kernel/setup.h b/arch/powerpc/kernel/setup.h index d144df54ad40..c6a592b67386 100644 --- a/arch/powerpc/kernel/setup.h +++ b/arch/powerpc/kernel/setup.h @@ -62,4 +62,10 @@ void kvm_cma_reserve(void); static inline void kvm_cma_reserve(void) { }; #endif +#ifdef CONFIG_TAU +u32 cpu_temp(unsigned long cpu); +u32 cpu_temp_both(unsigned long cpu); +u32 tau_interrupts(unsigned long cpu); +#endif /* CONFIG_TAU */ + #endif /* __ARCH_POWERPC_KERNEL_SETUP_H */ diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index b78f142a4148..7a7ce8ad455e 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -346,6 +346,13 @@ void __init early_setup(unsigned long dt_ptr) */ cpu_ready_for_interrupts(); + /* + * We enable ftrace here, but since we only support DYNAMIC_FTRACE, it + * will only actually get enabled on the boot cpu much later once + * ftrace itself has been initialized. + */ + this_cpu_enable_ftrace(); + DBG(" <- early_setup()\n"); #ifdef CONFIG_PPC_EARLY_DEBUG_BOOTX diff --git a/arch/powerpc/kernel/signal.h b/arch/powerpc/kernel/signal.h index a6467f843acf..800433685888 100644 --- a/arch/powerpc/kernel/signal.h +++ b/arch/powerpc/kernel/signal.h @@ -49,10 +49,8 @@ extern int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, #else /* CONFIG_PPC64 */ -extern long sys_rt_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8, - struct pt_regs *regs); -extern long sys_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8, - struct pt_regs *regs); +extern long sys_rt_sigreturn(void); +extern long sys_sigreturn(void); static inline int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, struct task_struct *tsk) diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 492f03451877..9cf8a03d3bc7 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -26,8 +26,8 @@ #include <linux/elf.h> #include <linux/ptrace.h> #include <linux/ratelimit.h> -#ifdef CONFIG_PPC64 #include <linux/syscalls.h> +#ifdef CONFIG_PPC64 #include <linux/compat.h> #else #include <linux/wait.h> @@ -57,10 +57,6 @@ #ifdef CONFIG_PPC64 -#define sys_rt_sigreturn compat_sys_rt_sigreturn -#define sys_swapcontext compat_sys_swapcontext -#define sys_sigreturn compat_sys_sigreturn - #define old_sigaction old_sigaction32 #define sigcontext sigcontext32 #define mcontext mcontext32 @@ -1041,10 +1037,15 @@ static int do_setcontext_tm(struct ucontext __user *ucp, } #endif -long sys_swapcontext(struct ucontext __user *old_ctx, - struct ucontext __user *new_ctx, - int ctx_size, int r6, int r7, int r8, struct pt_regs *regs) +#ifdef CONFIG_PPC64 +COMPAT_SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx, + struct ucontext __user *, new_ctx, int, ctx_size) +#else +SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx, + struct ucontext __user *, new_ctx, long, ctx_size) +#endif { + struct pt_regs *regs = current_pt_regs(); unsigned char tmp __maybe_unused; int ctx_has_vsx_region = 0; @@ -1132,10 +1133,14 @@ long sys_swapcontext(struct ucontext __user *old_ctx, return 0; } -long sys_rt_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8, - struct pt_regs *regs) +#ifdef CONFIG_PPC64 +COMPAT_SYSCALL_DEFINE0(rt_sigreturn) +#else +SYSCALL_DEFINE0(rt_sigreturn) +#endif { struct rt_sigframe __user *rt_sf; + struct pt_regs *regs = current_pt_regs(); #ifdef CONFIG_PPC_TRANSACTIONAL_MEM struct ucontext __user *uc_transact; unsigned long msr_hi; @@ -1224,11 +1229,10 @@ long sys_rt_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8, } #ifdef CONFIG_PPC32 -int sys_debug_setcontext(struct ucontext __user *ctx, - int ndbg, struct sig_dbg_op __user *dbg, - int r6, int r7, int r8, - struct pt_regs *regs) +SYSCALL_DEFINE3(debug_setcontext, struct ucontext __user *, ctx, + int, ndbg, struct sig_dbg_op __user *, dbg) { + struct pt_regs *regs = current_pt_regs(); struct sig_dbg_op op; int i; unsigned char tmp __maybe_unused; @@ -1419,9 +1423,13 @@ badframe: /* * Do a signal return; undo the signal stack. */ -long sys_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8, - struct pt_regs *regs) +#ifdef CONFIG_PPC64 +COMPAT_SYSCALL_DEFINE0(sigreturn) +#else +SYSCALL_DEFINE0(sigreturn) +#endif { + struct pt_regs *regs = current_pt_regs(); struct sigframe __user *sf; struct sigcontext __user *sc; struct sigcontext sigctx; diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 720117690822..83d51bf586c7 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -24,6 +24,7 @@ #include <linux/elf.h> #include <linux/ptrace.h> #include <linux/ratelimit.h> +#include <linux/syscalls.h> #include <asm/sigcontext.h> #include <asm/ucontext.h> @@ -624,17 +625,14 @@ static long setup_trampoline(unsigned int syscall, unsigned int __user *tramp) /* * Handle {get,set,swap}_context operations */ -int sys_swapcontext(struct ucontext __user *old_ctx, - struct ucontext __user *new_ctx, - long ctx_size, long r6, long r7, long r8, struct pt_regs *regs) +SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx, + struct ucontext __user *, new_ctx, long, ctx_size) { unsigned char tmp; sigset_t set; unsigned long new_msr = 0; int ctx_has_vsx_region = 0; - BUG_ON(regs != current->thread.regs); - if (new_ctx && get_user(new_msr, &new_ctx->uc_mcontext.gp_regs[PT_MSR])) return -EFAULT; @@ -698,18 +696,15 @@ int sys_swapcontext(struct ucontext __user *old_ctx, * Do a signal return; undo the signal stack. */ -int sys_rt_sigreturn(unsigned long r3, unsigned long r4, unsigned long r5, - unsigned long r6, unsigned long r7, unsigned long r8, - struct pt_regs *regs) +SYSCALL_DEFINE0(rt_sigreturn) { + struct pt_regs *regs = current_pt_regs(); struct ucontext __user *uc = (struct ucontext __user *)regs->gpr[1]; sigset_t set; #ifdef CONFIG_PPC_TRANSACTIONAL_MEM unsigned long msr; #endif - BUG_ON(current->thread.regs != regs); - /* Always make any pending restarted system calls return -EINTR */ current->restart_block.fn = do_no_restart_syscall; diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 9ca7148b5881..c96f8fbc1942 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -59,6 +59,7 @@ #include <asm/kexec.h> #include <asm/asm-prototypes.h> #include <asm/cpu_has_feature.h> +#include <asm/ftrace.h> #ifdef DEBUG #include <asm/udbg.h> @@ -1066,6 +1067,9 @@ void start_secondary(void *unused) local_irq_enable(); + /* We can enable ftrace for secondary cpus now */ + this_cpu_enable_ftrace(); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); BUG(); @@ -1162,6 +1166,8 @@ int __cpu_disable(void) if (!smp_ops->cpu_disable) return -ENOSYS; + this_cpu_disable_ftrace(); + err = smp_ops->cpu_disable(); if (err) return err; @@ -1180,6 +1186,12 @@ void __cpu_die(unsigned int cpu) void cpu_die(void) { + /* + * Disable on the down path. This will be re-enabled by + * start_secondary() via start_secondary_resume() below + */ + this_cpu_disable_ftrace(); + if (ppc_md.cpu_die) ppc_md.cpu_die(); diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c index d534ed901538..8dd6ba0c7d35 100644 --- a/arch/powerpc/kernel/stacktrace.c +++ b/arch/powerpc/kernel/stacktrace.c @@ -2,7 +2,7 @@ * Stack trace utility * * Copyright 2008 Christoph Hellwig, IBM Corp. - * + * Copyright 2018 SUSE Linux GmbH * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -11,11 +11,16 @@ */ #include <linux/export.h> +#include <linux/kallsyms.h> +#include <linux/module.h> #include <linux/sched.h> #include <linux/sched/debug.h> +#include <linux/sched/task_stack.h> #include <linux/stacktrace.h> #include <asm/ptrace.h> #include <asm/processor.h> +#include <linux/ftrace.h> +#include <asm/kprobes.h> /* * Save stack-backtrace addresses into a stack_trace buffer. @@ -76,3 +81,116 @@ save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace) save_context_stack(trace, regs->gpr[1], current, 0); } EXPORT_SYMBOL_GPL(save_stack_trace_regs); + +#ifdef CONFIG_HAVE_RELIABLE_STACKTRACE +int +save_stack_trace_tsk_reliable(struct task_struct *tsk, + struct stack_trace *trace) +{ + unsigned long sp; + unsigned long stack_page = (unsigned long)task_stack_page(tsk); + unsigned long stack_end; + int graph_idx = 0; + + /* + * The last frame (unwinding first) may not yet have saved + * its LR onto the stack. + */ + int firstframe = 1; + + if (tsk == current) + sp = current_stack_pointer(); + else + sp = tsk->thread.ksp; + + stack_end = stack_page + THREAD_SIZE; + if (!is_idle_task(tsk)) { + /* + * For user tasks, this is the SP value loaded on + * kernel entry, see "PACAKSAVE(r13)" in _switch() and + * system_call_common()/EXCEPTION_PROLOG_COMMON(). + * + * Likewise for non-swapper kernel threads, + * this also happens to be the top of the stack + * as setup by copy_thread(). + * + * Note that stack backlinks are not properly setup by + * copy_thread() and thus, a forked task() will have + * an unreliable stack trace until it's been + * _switch()'ed to for the first time. + */ + stack_end -= STACK_FRAME_OVERHEAD + sizeof(struct pt_regs); + } else { + /* + * idle tasks have a custom stack layout, + * c.f. cpu_idle_thread_init(). + */ + stack_end -= STACK_FRAME_OVERHEAD; + } + + if (sp < stack_page + sizeof(struct thread_struct) || + sp > stack_end - STACK_FRAME_MIN_SIZE) { + return 1; + } + + for (;;) { + unsigned long *stack = (unsigned long *) sp; + unsigned long newsp, ip; + + /* sanity check: ABI requires SP to be aligned 16 bytes. */ + if (sp & 0xF) + return 1; + + /* Mark stacktraces with exception frames as unreliable. */ + if (sp <= stack_end - STACK_INT_FRAME_SIZE && + stack[STACK_FRAME_MARKER] == STACK_FRAME_REGS_MARKER) { + return 1; + } + + newsp = stack[0]; + /* Stack grows downwards; unwinder may only go up. */ + if (newsp <= sp) + return 1; + + if (newsp != stack_end && + newsp > stack_end - STACK_FRAME_MIN_SIZE) { + return 1; /* invalid backlink, too far up. */ + } + + /* Examine the saved LR: it must point into kernel code. */ + ip = stack[STACK_FRAME_LR_SAVE]; + if (!firstframe && !__kernel_text_address(ip)) + return 1; + firstframe = 0; + + /* + * FIXME: IMHO these tests do not belong in + * arch-dependent code, they are generic. + */ + ip = ftrace_graph_ret_addr(tsk, &graph_idx, ip, NULL); +#ifdef CONFIG_KPROBES + /* + * Mark stacktraces with kretprobed functions on them + * as unreliable. + */ + if (ip == (unsigned long)kretprobe_trampoline) + return 1; +#endif + + if (!trace->skip) + trace->entries[trace->nr_entries++] = ip; + else + trace->skip--; + + if (newsp == stack_end) + break; + + if (trace->nr_entries >= trace->max_entries) + return -E2BIG; + + sp = newsp; + } + return 0; +} +EXPORT_SYMBOL_GPL(save_stack_trace_tsk_reliable); +#endif /* CONFIG_HAVE_RELIABLE_STACKTRACE */ diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c index c11c73373691..bdf58ba1a94b 100644 --- a/arch/powerpc/kernel/sys_ppc32.c +++ b/arch/powerpc/kernel/sys_ppc32.c @@ -52,15 +52,6 @@ #include <asm/syscalls.h> #include <asm/switch_to.h> - -asmlinkage long ppc32_select(u32 n, compat_ulong_t __user *inp, - compat_ulong_t __user *outp, compat_ulong_t __user *exp, - compat_uptr_t tvp_x) -{ - /* sign extend n */ - return compat_sys_select((int)n, inp, outp, exp, compat_ptr(tvp_x)); -} - unsigned long compat_sys_mmap2(unsigned long addr, size_t len, unsigned long prot, unsigned long flags, unsigned long fd, unsigned long pgoff) diff --git a/arch/powerpc/kernel/systbl.S b/arch/powerpc/kernel/systbl.S index 7ccb7f81f8db..919a32746ede 100644 --- a/arch/powerpc/kernel/systbl.S +++ b/arch/powerpc/kernel/systbl.S @@ -35,7 +35,7 @@ #endif #define SYSCALL_SPU(func) SYSCALL(func) #define COMPAT_SYS_SPU(func) COMPAT_SYS(func) -#define PPC_SYS_SPU(func) PPC_SYS(func) +#define COMPAT_SPU_NEW(func) COMPAT_SYS(func) #define SYSX_SPU(f, f3264, f32) SYSX(f, f3264, f32) .section .rodata,"a" diff --git a/arch/powerpc/kernel/systbl_chk.c b/arch/powerpc/kernel/systbl_chk.c index 55323a620cfe..4653258722ac 100644 --- a/arch/powerpc/kernel/systbl_chk.c +++ b/arch/powerpc/kernel/systbl_chk.c @@ -31,7 +31,7 @@ #define SYSCALL_SPU(func) SYSCALL(func) #define COMPAT_SYS_SPU(func) COMPAT_SYS(func) -#define PPC_SYS_SPU(func) PPC_SYS(func) +#define COMPAT_SPU_NEW(func) COMPAT_SYS(_new##func) #define SYSX_SPU(f, f3264, f32) SYSX(f, f3264, f32) /* Just insert a marker for ni_syscalls */ diff --git a/arch/powerpc/kernel/systbl_chk.sh b/arch/powerpc/kernel/systbl_chk.sh index 31b6e7c358ca..f2e356c2a345 100644 --- a/arch/powerpc/kernel/systbl_chk.sh +++ b/arch/powerpc/kernel/systbl_chk.sh @@ -16,7 +16,7 @@ awk 'BEGIN { num = -1; } # Ignore the beginning of the file /^START_TABLE/ { num = 0; next; } /^END_TABLE/ { if (num != $2) { - printf "NR_syscalls (%s) is not one more than the last syscall (%s)\n", + printf "Error: NR_syscalls (%s) is not one more than the last syscall (%s)\n", $2, num - 1; exit(1); } @@ -25,7 +25,7 @@ awk 'BEGIN { num = -1; } # Ignore the beginning of the file { if (num == -1) next; if (($1 != -1) && ($1 != num)) { - printf "Syscall %s out of order (expected %s)\n", + printf "Error: Syscall %s out of order (expected %s)\n", $1, num; exit(1); }; diff --git a/arch/powerpc/kernel/tau_6xx.c b/arch/powerpc/kernel/tau_6xx.c index 8cdd852aedd1..e2ab8a111b69 100644 --- a/arch/powerpc/kernel/tau_6xx.c +++ b/arch/powerpc/kernel/tau_6xx.c @@ -27,6 +27,9 @@ #include <asm/cache.h> #include <asm/8xx_immap.h> #include <asm/machdep.h> +#include <asm/asm-prototypes.h> + +#include "setup.h" static struct tau_temp { @@ -50,7 +53,7 @@ struct timer_list tau_timer; #define shrink_timer 2*HZ /* period between shrinking the window */ #define min_window 2 /* minimum window size, degrees C */ -void set_thresholds(unsigned long cpu) +static void set_thresholds(unsigned long cpu) { #ifdef CONFIG_TAU_INT /* @@ -70,7 +73,7 @@ void set_thresholds(unsigned long cpu) #endif } -void TAUupdate(int cpu) +static void TAUupdate(int cpu) { unsigned thrm; @@ -205,7 +208,7 @@ static void tau_timeout_smp(struct timer_list *unused) int tau_initialized = 0; -void __init TAU_init_smp(void * info) +static void __init TAU_init_smp(void *info) { unsigned long cpu = smp_processor_id(); @@ -217,7 +220,7 @@ void __init TAU_init_smp(void * info) set_thresholds(cpu); } -int __init TAU_init(void) +static int __init TAU_init(void) { /* We assume in SMP that if one CPU has TAU support, they * all have it --BenH @@ -259,12 +262,12 @@ u32 cpu_temp_both(unsigned long cpu) return ((tau[cpu].high << 16) | tau[cpu].low); } -int cpu_temp(unsigned long cpu) +u32 cpu_temp(unsigned long cpu) { return ((tau[cpu].high + tau[cpu].low) / 2); } -int tau_interrupts(unsigned long cpu) +u32 tau_interrupts(unsigned long cpu) { return (tau[cpu].interrupts); } diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S index b92ac8e711db..ff12f47a96b6 100644 --- a/arch/powerpc/kernel/tm.S +++ b/arch/powerpc/kernel/tm.S @@ -12,6 +12,7 @@ #include <asm/ptrace.h> #include <asm/reg.h> #include <asm/bug.h> +#include <asm/export.h> #ifdef CONFIG_VSX /* See fpu.S, this is borrowed from there */ @@ -55,6 +56,16 @@ _GLOBAL(tm_enable) or r4, r4, r3 mtmsrd r4 1: blr +EXPORT_SYMBOL_GPL(tm_enable); + +_GLOBAL(tm_disable) + mfmsr r4 + li r3, MSR_TM >> 32 + sldi r3, r3, 32 + andc r4, r4, r3 + mtmsrd r4 + blr +EXPORT_SYMBOL_GPL(tm_disable); _GLOBAL(tm_save_sprs) mfspr r0, SPRN_TFHAR @@ -78,6 +89,7 @@ _GLOBAL(tm_restore_sprs) _GLOBAL(tm_abort) TABORT(R3) blr +EXPORT_SYMBOL_GPL(tm_abort); /* void tm_reclaim(struct thread_struct *thread, * uint8_t cause) diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c index 4741fe112f05..c076a32093fd 100644 --- a/arch/powerpc/kernel/trace/ftrace.c +++ b/arch/powerpc/kernel/trace/ftrace.c @@ -357,6 +357,8 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) { unsigned int op[2]; void *ip = (void *)rec->ip; + unsigned long entry, ptr, tramp; + struct module *mod = rec->arch.mod; /* read where this goes */ if (probe_kernel_read(op, ip, sizeof(op))) @@ -368,19 +370,44 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) return -EINVAL; } - /* If we never set up a trampoline to ftrace_caller, then bail */ - if (!rec->arch.mod->arch.tramp) { + /* If we never set up ftrace trampoline(s), then bail */ +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS + if (!mod->arch.tramp || !mod->arch.tramp_regs) { +#else + if (!mod->arch.tramp) { +#endif pr_err("No ftrace trampoline\n"); return -EINVAL; } +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS + if (rec->flags & FTRACE_FL_REGS) + tramp = mod->arch.tramp_regs; + else +#endif + tramp = mod->arch.tramp; + + if (module_trampoline_target(mod, tramp, &ptr)) { + pr_err("Failed to get trampoline target\n"); + return -EFAULT; + } + + pr_devel("trampoline target %lx", ptr); + + entry = ppc_global_function_entry((void *)addr); + /* This should match what was called */ + if (ptr != entry) { + pr_err("addr %lx does not match expected %lx\n", ptr, entry); + return -EINVAL; + } + /* Ensure branch is within 24 bits */ - if (!create_branch(ip, rec->arch.mod->arch.tramp, BRANCH_SET_LINK)) { + if (!create_branch(ip, tramp, BRANCH_SET_LINK)) { pr_err("Branch out of range\n"); return -EINVAL; } - if (patch_branch(ip, rec->arch.mod->arch.tramp, BRANCH_SET_LINK)) { + if (patch_branch(ip, tramp, BRANCH_SET_LINK)) { pr_err("REL24 out of range!\n"); return -EINVAL; } @@ -388,14 +415,6 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) return 0; } -#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS -int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, - unsigned long addr) -{ - return ftrace_make_call(rec, addr); -} -#endif - #else /* !CONFIG_PPC64: */ static int __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) @@ -472,53 +491,158 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) #endif /* CONFIG_MODULES */ } -int ftrace_update_ftrace_func(ftrace_func_t func) +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +#ifdef CONFIG_MODULES +static int +__ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, + unsigned long addr) { - unsigned long ip = (unsigned long)(&ftrace_call); - unsigned int old, new; - int ret; + unsigned int op; + unsigned long ip = rec->ip; + unsigned long entry, ptr, tramp; + struct module *mod = rec->arch.mod; - old = *(unsigned int *)&ftrace_call; - new = ftrace_call_replace(ip, (unsigned long)func, 1); - ret = ftrace_modify_code(ip, old, new); + /* If we never set up ftrace trampolines, then bail */ + if (!mod->arch.tramp || !mod->arch.tramp_regs) { + pr_err("No ftrace trampoline\n"); + return -EINVAL; + } - return ret; -} + /* read where this goes */ + if (probe_kernel_read(&op, (void *)ip, sizeof(int))) { + pr_err("Fetching opcode failed.\n"); + return -EFAULT; + } -static int __ftrace_replace_code(struct dyn_ftrace *rec, int enable) -{ - unsigned long ftrace_addr = (unsigned long)FTRACE_ADDR; - int ret; + /* Make sure that that this is still a 24bit jump */ + if (!is_bl_op(op)) { + pr_err("Not expected bl: opcode is %x\n", op); + return -EINVAL; + } + + /* lets find where the pointer goes */ + tramp = find_bl_target(ip, op); + entry = ppc_global_function_entry((void *)old_addr); + + pr_devel("ip:%lx jumps to %lx", ip, tramp); - ret = ftrace_update_record(rec, enable); + if (tramp != entry) { + /* old_addr is not within range, so we must have used a trampoline */ + if (module_trampoline_target(mod, tramp, &ptr)) { + pr_err("Failed to get trampoline target\n"); + return -EFAULT; + } + + pr_devel("trampoline target %lx", ptr); + + /* This should match what was called */ + if (ptr != entry) { + pr_err("addr %lx does not match expected %lx\n", ptr, entry); + return -EINVAL; + } + } + + /* The new target may be within range */ + if (test_24bit_addr(ip, addr)) { + /* within range */ + if (patch_branch((unsigned int *)ip, addr, BRANCH_SET_LINK)) { + pr_err("REL24 out of range!\n"); + return -EINVAL; + } - switch (ret) { - case FTRACE_UPDATE_IGNORE: return 0; - case FTRACE_UPDATE_MAKE_CALL: - return ftrace_make_call(rec, ftrace_addr); - case FTRACE_UPDATE_MAKE_NOP: - return ftrace_make_nop(NULL, rec, ftrace_addr); + } + + if (rec->flags & FTRACE_FL_REGS) + tramp = mod->arch.tramp_regs; + else + tramp = mod->arch.tramp; + + if (module_trampoline_target(mod, tramp, &ptr)) { + pr_err("Failed to get trampoline target\n"); + return -EFAULT; + } + + pr_devel("trampoline target %lx", ptr); + + entry = ppc_global_function_entry((void *)addr); + /* This should match what was called */ + if (ptr != entry) { + pr_err("addr %lx does not match expected %lx\n", ptr, entry); + return -EINVAL; + } + + /* Ensure branch is within 24 bits */ + if (!create_branch((unsigned int *)ip, tramp, BRANCH_SET_LINK)) { + pr_err("Branch out of range\n"); + return -EINVAL; + } + + if (patch_branch((unsigned int *)ip, tramp, BRANCH_SET_LINK)) { + pr_err("REL24 out of range!\n"); + return -EINVAL; } return 0; } +#endif -void ftrace_replace_code(int enable) +int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, + unsigned long addr) { - struct ftrace_rec_iter *iter; - struct dyn_ftrace *rec; + unsigned long ip = rec->ip; + unsigned int old, new; + + /* + * If the calling address is more that 24 bits away, + * then we had to use a trampoline to make the call. + * Otherwise just update the call site. + */ + if (test_24bit_addr(ip, addr) && test_24bit_addr(ip, old_addr)) { + /* within range */ + old = ftrace_call_replace(ip, old_addr, 1); + new = ftrace_call_replace(ip, addr, 1); + return ftrace_modify_code(ip, old, new); + } + +#ifdef CONFIG_MODULES + /* + * Out of range jumps are called from modules. + */ + if (!rec->arch.mod) { + pr_err("No module loaded\n"); + return -EINVAL; + } + + return __ftrace_modify_call(rec, old_addr, addr); +#else + /* We should not get here without modules */ + return -EINVAL; +#endif /* CONFIG_MODULES */ +} +#endif + +int ftrace_update_ftrace_func(ftrace_func_t func) +{ + unsigned long ip = (unsigned long)(&ftrace_call); + unsigned int old, new; int ret; - for (iter = ftrace_rec_iter_start(); iter; - iter = ftrace_rec_iter_next(iter)) { - rec = ftrace_rec_iter_record(iter); - ret = __ftrace_replace_code(rec, enable); - if (ret) { - ftrace_bug(ret, rec); - return; - } + old = *(unsigned int *)&ftrace_call; + new = ftrace_call_replace(ip, (unsigned long)func, 1); + ret = ftrace_modify_code(ip, old, new); + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS + /* Also update the regs callback function */ + if (!ret) { + ip = (unsigned long)(&ftrace_regs_call); + old = *(unsigned int *)&ftrace_regs_call; + new = ftrace_call_replace(ip, (unsigned long)func, 1); + ret = ftrace_modify_code(ip, old, new); } +#endif + + return ret; } /* @@ -538,7 +662,6 @@ int __init ftrace_dyn_arch_init(void) #ifdef CONFIG_FUNCTION_GRAPH_TRACER -#ifdef CONFIG_DYNAMIC_FTRACE extern void ftrace_graph_call(void); extern void ftrace_graph_stub(void); @@ -567,7 +690,6 @@ int ftrace_disable_ftrace_graph_caller(void) return ftrace_modify_code(ip, old, new); } -#endif /* CONFIG_DYNAMIC_FTRACE */ /* * Hook the return address and push it in the stack of return addrs diff --git a/arch/powerpc/kernel/trace/ftrace_32.S b/arch/powerpc/kernel/trace/ftrace_32.S index afef2c076282..2c29098f630f 100644 --- a/arch/powerpc/kernel/trace/ftrace_32.S +++ b/arch/powerpc/kernel/trace/ftrace_32.S @@ -14,7 +14,6 @@ #include <asm/ftrace.h> #include <asm/export.h> -#ifdef CONFIG_DYNAMIC_FTRACE _GLOBAL(mcount) _GLOBAL(_mcount) /* @@ -47,26 +46,7 @@ _GLOBAL(ftrace_graph_stub) MCOUNT_RESTORE_FRAME /* old link register ends up in ctr reg */ bctr -#else -_GLOBAL(mcount) -_GLOBAL(_mcount) - - MCOUNT_SAVE_FRAME - subi r3, r3, MCOUNT_INSN_SIZE - LOAD_REG_ADDR(r5, ftrace_trace_function) - lwz r5,0(r5) - - mtctr r5 - bctrl - nop - -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - b ftrace_graph_caller -#endif - MCOUNT_RESTORE_FRAME - bctr -#endif EXPORT_SYMBOL(_mcount) _GLOBAL(ftrace_stub) diff --git a/arch/powerpc/kernel/trace/ftrace_64.S b/arch/powerpc/kernel/trace/ftrace_64.S index e5ccea19821e..e25f77c10a72 100644 --- a/arch/powerpc/kernel/trace/ftrace_64.S +++ b/arch/powerpc/kernel/trace/ftrace_64.S @@ -14,7 +14,6 @@ #include <asm/ppc-opcode.h> #include <asm/export.h> -#ifdef CONFIG_DYNAMIC_FTRACE _GLOBAL(mcount) _GLOBAL(_mcount) EXPORT_SYMBOL(_mcount) @@ -23,34 +22,6 @@ EXPORT_SYMBOL(_mcount) mtlr r0 bctr -#else /* CONFIG_DYNAMIC_FTRACE */ -_GLOBAL_TOC(_mcount) -EXPORT_SYMBOL(_mcount) - /* Taken from output of objdump from lib64/glibc */ - mflr r3 - ld r11, 0(r1) - stdu r1, -112(r1) - std r3, 128(r1) - ld r4, 16(r11) - - subi r3, r3, MCOUNT_INSN_SIZE - LOAD_REG_ADDR(r5,ftrace_trace_function) - ld r5,0(r5) - ld r5,0(r5) - mtctr r5 - bctrl - nop - -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - b ftrace_graph_caller -#endif - ld r0, 128(r1) - mtlr r0 - addi r1, r1, 112 -_GLOBAL(ftrace_stub) - blr -#endif /* CONFIG_DYNAMIC_FTRACE */ - #ifdef CONFIG_FUNCTION_GRAPH_TRACER _GLOBAL(return_to_handler) /* need to save return values */ diff --git a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S index 3f3e81852422..9a5b5a513604 100644 --- a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S +++ b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S @@ -17,11 +17,10 @@ #include <asm/bug.h> #include <asm/ptrace.h> -#ifdef CONFIG_DYNAMIC_FTRACE /* * - * ftrace_caller() is the function that replaces _mcount() when ftrace is - * active. + * ftrace_caller()/ftrace_regs_caller() is the function that replaces _mcount() + * when ftrace is active. * * We arrive here after a function A calls function B, and we are the trace * function for B. When we enter r1 points to A's stack frame, B has not yet @@ -37,7 +36,7 @@ * Our job is to save the register state into a struct pt_regs (on the stack) * and then arrange for the ftrace function to be called. */ -_GLOBAL(ftrace_caller) +_GLOBAL(ftrace_regs_caller) /* Save the original return address in A's stack frame */ std r0,LRSAVE(r1) @@ -47,6 +46,12 @@ _GLOBAL(ftrace_caller) /* Save all gprs to pt_regs */ SAVE_GPR(0, r1) SAVE_10GPRS(2, r1) + + /* Ok to continue? */ + lbz r3, PACA_FTRACE_ENABLED(r13) + cmpdi r3, 0 + beq ftrace_no_trace + SAVE_10GPRS(12, r1) SAVE_10GPRS(22, r1) @@ -94,8 +99,8 @@ _GLOBAL(ftrace_caller) addi r6, r1 ,STACK_FRAME_OVERHEAD /* ftrace_call(r3, r4, r5, r6) */ -.globl ftrace_call -ftrace_call: +.globl ftrace_regs_call +ftrace_regs_call: bl ftrace_stub nop @@ -156,6 +161,7 @@ ftrace_call: bne- livepatch_handler #endif +ftrace_caller_common: #ifdef CONFIG_FUNCTION_GRAPH_TRACER .globl ftrace_graph_call ftrace_graph_call: @@ -168,6 +174,74 @@ _GLOBAL(ftrace_graph_stub) _GLOBAL(ftrace_stub) blr +ftrace_no_trace: + mflr r3 + mtctr r3 + REST_GPR(3, r1) + addi r1, r1, SWITCH_FRAME_SIZE + mtlr r0 + bctr + +_GLOBAL(ftrace_caller) + /* Save the original return address in A's stack frame */ + std r0, LRSAVE(r1) + + /* Create our stack frame + pt_regs */ + stdu r1, -SWITCH_FRAME_SIZE(r1) + + /* Save all gprs to pt_regs */ + SAVE_8GPRS(3, r1) + + lbz r3, PACA_FTRACE_ENABLED(r13) + cmpdi r3, 0 + beq ftrace_no_trace + + /* Get the _mcount() call site out of LR */ + mflr r7 + std r7, _NIP(r1) + + /* Save callee's TOC in the ABI compliant location */ + std r2, 24(r1) + ld r2, PACATOC(r13) /* get kernel TOC in r2 */ + + addis r3, r2, function_trace_op@toc@ha + addi r3, r3, function_trace_op@toc@l + ld r5, 0(r3) + + /* Calculate ip from nip-4 into r3 for call below */ + subi r3, r7, MCOUNT_INSN_SIZE + + /* Put the original return address in r4 as parent_ip */ + mr r4, r0 + + /* Set pt_regs to NULL */ + li r6, 0 + + /* ftrace_call(r3, r4, r5, r6) */ +.globl ftrace_call +ftrace_call: + bl ftrace_stub + nop + + ld r3, _NIP(r1) + mtctr r3 + + /* Restore gprs */ + REST_8GPRS(3,r1) + + /* Restore callee's TOC */ + ld r2, 24(r1) + + /* Pop our stack frame */ + addi r1, r1, SWITCH_FRAME_SIZE + + /* Reload original LR */ + ld r0, LRSAVE(r1) + mtlr r0 + + /* Handle function_graph or go back */ + b ftrace_caller_common + #ifdef CONFIG_LIVEPATCH /* * This function runs in the mcount context, between two functions. As @@ -236,8 +310,6 @@ livepatch_handler: blr #endif /* CONFIG_LIVEPATCH */ -#endif /* CONFIG_DYNAMIC_FTRACE */ - #ifdef CONFIG_FUNCTION_GRAPH_TRACER _GLOBAL(ftrace_graph_caller) stdu r1, -112(r1) diff --git a/arch/powerpc/kernel/trace/ftrace_64_pg.S b/arch/powerpc/kernel/trace/ftrace_64_pg.S index f095358da96e..4c515c4023de 100644 --- a/arch/powerpc/kernel/trace/ftrace_64_pg.S +++ b/arch/powerpc/kernel/trace/ftrace_64_pg.S @@ -14,8 +14,11 @@ #include <asm/ppc-opcode.h> #include <asm/export.h> -#ifdef CONFIG_DYNAMIC_FTRACE _GLOBAL_TOC(ftrace_caller) + lbz r3, PACA_FTRACE_ENABLED(r13) + cmpdi r3, 0 + beqlr + /* Taken from output of objdump from lib64/glibc */ mflr r3 ld r11, 0(r1) @@ -39,7 +42,6 @@ _GLOBAL(ftrace_graph_stub) _GLOBAL(ftrace_stub) blr -#endif /* CONFIG_DYNAMIC_FTRACE */ #ifdef CONFIG_FUNCTION_GRAPH_TRACER _GLOBAL(ftrace_graph_caller) diff --git a/arch/powerpc/kernel/vecemu.c b/arch/powerpc/kernel/vecemu.c index 8812085883fd..4acd3fb2b38e 100644 --- a/arch/powerpc/kernel/vecemu.c +++ b/arch/powerpc/kernel/vecemu.c @@ -8,6 +8,7 @@ #include <linux/sched.h> #include <asm/ptrace.h> #include <asm/processor.h> +#include <asm/switch_to.h> #include <linux/uaccess.h> /* Functions in vector.S */ diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c index 6256dc3b0087..1d82274f7e9f 100644 --- a/arch/powerpc/kernel/watchdog.c +++ b/arch/powerpc/kernel/watchdog.c @@ -64,7 +64,7 @@ * means the CPU(s) with their bit still set in the pending mask have had * their heartbeat stop, and action is taken. * - * Some platforms implement true NMI IPIs, which can by used by the SMP + * Some platforms implement true NMI IPIs, which can be used by the SMP * watchdog to detect an unresponsive CPU and pull it out of its stuck * state with the NMI IPI, to get crash/debug data from it. This way the * SMP watchdog can detect hardware interrupts off lockups. @@ -111,7 +111,13 @@ static inline void wd_smp_unlock(unsigned long *flags) static void wd_lockup_ipi(struct pt_regs *regs) { - pr_emerg("CPU %d Hard LOCKUP\n", raw_smp_processor_id()); + int cpu = raw_smp_processor_id(); + u64 tb = get_tb(); + + pr_emerg("CPU %d Hard LOCKUP\n", cpu); + pr_emerg("CPU %d TB:%lld, last heartbeat TB:%lld (%lldms ago)\n", + cpu, tb, per_cpu(wd_timer_tb, cpu), + tb_to_ns(tb - per_cpu(wd_timer_tb, cpu)) / 1000000); print_modules(); print_irqtrace_events(current); if (regs) @@ -154,6 +160,9 @@ static void watchdog_smp_panic(int cpu, u64 tb) pr_emerg("CPU %d detected hard LOCKUP on other CPUs %*pbl\n", cpu, cpumask_pr_args(&wd_smp_cpus_pending)); + pr_emerg("CPU %d TB:%lld, last SMP heartbeat TB:%lld (%lldms ago)\n", + cpu, tb, wd_smp_last_reset_tb, + tb_to_ns(tb - wd_smp_last_reset_tb) / 1000000); if (!sysctl_hardlockup_all_cpu_backtrace) { /* @@ -194,10 +203,19 @@ static void wd_smp_clear_cpu_pending(int cpu, u64 tb) { if (!cpumask_test_cpu(cpu, &wd_smp_cpus_pending)) { if (unlikely(cpumask_test_cpu(cpu, &wd_smp_cpus_stuck))) { + struct pt_regs *regs = get_irq_regs(); unsigned long flags; - pr_emerg("CPU %d became unstuck\n", cpu); wd_smp_lock(&flags); + + pr_emerg("CPU %d became unstuck TB:%lld\n", + cpu, tb); + print_irqtrace_events(current); + if (regs) + show_regs(regs); + else + dump_stack(); + cpumask_clear_cpu(cpu, &wd_smp_cpus_stuck); wd_smp_unlock(&flags); } @@ -245,8 +263,6 @@ void soft_nmi_interrupt(struct pt_regs *regs) tb = get_tb(); if (tb - per_cpu(wd_timer_tb, cpu) >= wd_panic_timeout_tb) { - per_cpu(wd_timer_tb, cpu) = tb; - wd_smp_lock(&flags); if (cpumask_test_cpu(cpu, &wd_smp_cpus_stuck)) { wd_smp_unlock(&flags); @@ -254,7 +270,11 @@ void soft_nmi_interrupt(struct pt_regs *regs) } set_cpu_stuck(cpu, tb); - pr_emerg("CPU %d self-detected hard LOCKUP @ %pS\n", cpu, (void *)regs->nip); + pr_emerg("CPU %d self-detected hard LOCKUP @ %pS\n", + cpu, (void *)regs->nip); + pr_emerg("CPU %d TB:%lld, last heartbeat TB:%lld (%lldms ago)\n", + cpu, tb, per_cpu(wd_timer_tb, cpu), + tb_to_ns(tb - per_cpu(wd_timer_tb, cpu)) / 1000000); print_modules(); print_irqtrace_events(current); show_regs(regs); diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index a57eafec4dc2..ccdf3761eec0 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -200,6 +200,7 @@ void kvmppc_radix_set_pte_at(struct kvm *kvm, unsigned long addr, } static struct kmem_cache *kvm_pte_cache; +static struct kmem_cache *kvm_pmd_cache; static pte_t *kvmppc_pte_alloc(void) { @@ -217,6 +218,16 @@ static inline int pmd_is_leaf(pmd_t pmd) return !!(pmd_val(pmd) & _PAGE_PTE); } +static pmd_t *kvmppc_pmd_alloc(void) +{ + return kmem_cache_alloc(kvm_pmd_cache, GFP_KERNEL); +} + +static void kvmppc_pmd_free(pmd_t *pmdp) +{ + kmem_cache_free(kvm_pmd_cache, pmdp); +} + static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa, unsigned int level, unsigned long mmu_seq) { @@ -239,7 +250,7 @@ static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa, if (pud && pud_present(*pud) && !pud_huge(*pud)) pmd = pmd_offset(pud, gpa); else if (level <= 1) - new_pmd = pmd_alloc_one(kvm->mm, gpa); + new_pmd = kvmppc_pmd_alloc(); if (level == 0 && !(pmd && pmd_present(*pmd) && !pmd_is_leaf(*pmd))) new_ptep = kvmppc_pte_alloc(); @@ -382,7 +393,7 @@ static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa, if (new_pud) pud_free(kvm->mm, new_pud); if (new_pmd) - pmd_free(kvm->mm, new_pmd); + kvmppc_pmd_free(new_pmd); if (new_ptep) kvmppc_pte_free(new_ptep); return ret; @@ -758,7 +769,7 @@ void kvmppc_free_radix(struct kvm *kvm) kvmppc_pte_free(pte); pmd_clear(pmd); } - pmd_free(kvm->mm, pmd_offset(pud, 0)); + kvmppc_pmd_free(pmd_offset(pud, 0)); pud_clear(pud); } pud_free(kvm->mm, pud_offset(pgd, 0)); @@ -770,20 +781,35 @@ void kvmppc_free_radix(struct kvm *kvm) static void pte_ctor(void *addr) { - memset(addr, 0, PTE_TABLE_SIZE); + memset(addr, 0, RADIX_PTE_TABLE_SIZE); +} + +static void pmd_ctor(void *addr) +{ + memset(addr, 0, RADIX_PMD_TABLE_SIZE); } int kvmppc_radix_init(void) { - unsigned long size = sizeof(void *) << PTE_INDEX_SIZE; + unsigned long size = sizeof(void *) << RADIX_PTE_INDEX_SIZE; kvm_pte_cache = kmem_cache_create("kvm-pte", size, size, 0, pte_ctor); if (!kvm_pte_cache) return -ENOMEM; + + size = sizeof(void *) << RADIX_PMD_INDEX_SIZE; + + kvm_pmd_cache = kmem_cache_create("kvm-pmd", size, size, 0, pmd_ctor); + if (!kvm_pmd_cache) { + kmem_cache_destroy(kvm_pte_cache); + return -ENOMEM; + } + return 0; } void kvmppc_radix_exit(void) { kmem_cache_destroy(kvm_pte_cache); + kmem_cache_destroy(kvm_pmd_cache); } diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 4d07fca5121c..f604cbd8fc34 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -2911,8 +2911,12 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) srcu_idx = srcu_read_lock(&vc->kvm->srcu); + this_cpu_disable_ftrace(); + trap = __kvmppc_vcore_entry(); + this_cpu_enable_ftrace(); + srcu_read_unlock(&vc->kvm->srcu, srcu_idx); trace_hardirqs_off(); diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index bd63fa8a08b5..2c3cbe0067b2 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -342,6 +342,9 @@ kvm_start_guest: ld r2,PACATOC(r13) + li r0,0 + stb r0,PACA_FTRACE_ENABLED(r13) + li r0,KVM_HWTHREAD_IN_KVM stb r0,HSTATE_HWTHREAD_STATE(r13) diff --git a/arch/powerpc/lib/feature-fixups-test.S b/arch/powerpc/lib/feature-fixups-test.S index f4613118132e..f16cec989506 100644 --- a/arch/powerpc/lib/feature-fixups-test.S +++ b/arch/powerpc/lib/feature-fixups-test.S @@ -167,16 +167,52 @@ globl(ftr_fixup_test6_expected) blt 2b b 3f b 1b -2: or 1,1,1 +3: or 1,1,1 + or 2,2,2 + or 3,3,3 + +globl(ftr_fixup_test7) + or 1,1,1 +BEGIN_FTR_SECTION + or 2,2,2 + or 2,2,2 or 2,2,2 -3: or 3,3,3 + or 2,2,2 + or 2,2,2 + or 2,2,2 + or 2,2,2 +FTR_SECTION_ELSE +2: b 3f +3: or 5,5,5 + beq 3b + b 1f + or 6,6,6 + b 2b + bdnz 3b +1: +ALT_FTR_SECTION_END(0, 1) + or 1,1,1 + or 1,1,1 + +globl(end_ftr_fixup_test7) + nop +globl(ftr_fixup_test7_expected) + or 1,1,1 +2: b 3f +3: or 5,5,5 + beq 3b + b 1f + or 6,6,6 + b 2b + bdnz 3b +1: or 1,1,1 #if 0 /* Test that if we have a larger else case the assembler spots it and * reports an error. #if 0'ed so as not to break the build normally. */ -ftr_fixup_test7: +ftr_fixup_test_too_big: or 1,1,1 BEGIN_FTR_SECTION or 2,2,2 diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c index 288fe4f0db4e..f3e46d4edd72 100644 --- a/arch/powerpc/lib/feature-fixups.c +++ b/arch/powerpc/lib/feature-fixups.c @@ -285,7 +285,7 @@ static void test_basic_patching(void) extern unsigned int end_ftr_fixup_test1[]; extern unsigned int ftr_fixup_test1_orig[]; extern unsigned int ftr_fixup_test1_expected[]; - int size = end_ftr_fixup_test1 - ftr_fixup_test1; + int size = 4 * (end_ftr_fixup_test1 - ftr_fixup_test1); fixup.value = fixup.mask = 8; fixup.start_off = calc_offset(&fixup, ftr_fixup_test1 + 1); @@ -317,7 +317,7 @@ static void test_alternative_patching(void) extern unsigned int ftr_fixup_test2_orig[]; extern unsigned int ftr_fixup_test2_alt[]; extern unsigned int ftr_fixup_test2_expected[]; - int size = end_ftr_fixup_test2 - ftr_fixup_test2; + int size = 4 * (end_ftr_fixup_test2 - ftr_fixup_test2); fixup.value = fixup.mask = 0xF; fixup.start_off = calc_offset(&fixup, ftr_fixup_test2 + 1); @@ -349,7 +349,7 @@ static void test_alternative_case_too_big(void) extern unsigned int end_ftr_fixup_test3[]; extern unsigned int ftr_fixup_test3_orig[]; extern unsigned int ftr_fixup_test3_alt[]; - int size = end_ftr_fixup_test3 - ftr_fixup_test3; + int size = 4 * (end_ftr_fixup_test3 - ftr_fixup_test3); fixup.value = fixup.mask = 0xC; fixup.start_off = calc_offset(&fixup, ftr_fixup_test3 + 1); @@ -376,7 +376,7 @@ static void test_alternative_case_too_small(void) extern unsigned int ftr_fixup_test4_orig[]; extern unsigned int ftr_fixup_test4_alt[]; extern unsigned int ftr_fixup_test4_expected[]; - int size = end_ftr_fixup_test4 - ftr_fixup_test4; + int size = 4 * (end_ftr_fixup_test4 - ftr_fixup_test4); unsigned long flag; /* Check a high-bit flag */ @@ -410,7 +410,7 @@ static void test_alternative_case_with_branch(void) extern unsigned int ftr_fixup_test5[]; extern unsigned int end_ftr_fixup_test5[]; extern unsigned int ftr_fixup_test5_expected[]; - int size = end_ftr_fixup_test5 - ftr_fixup_test5; + int size = 4 * (end_ftr_fixup_test5 - ftr_fixup_test5); check(memcmp(ftr_fixup_test5, ftr_fixup_test5_expected, size) == 0); } @@ -420,11 +420,21 @@ static void test_alternative_case_with_external_branch(void) extern unsigned int ftr_fixup_test6[]; extern unsigned int end_ftr_fixup_test6[]; extern unsigned int ftr_fixup_test6_expected[]; - int size = end_ftr_fixup_test6 - ftr_fixup_test6; + int size = 4 * (end_ftr_fixup_test6 - ftr_fixup_test6); check(memcmp(ftr_fixup_test6, ftr_fixup_test6_expected, size) == 0); } +static void test_alternative_case_with_branch_to_end(void) +{ + extern unsigned int ftr_fixup_test7[]; + extern unsigned int end_ftr_fixup_test7[]; + extern unsigned int ftr_fixup_test7_expected[]; + int size = 4 * (end_ftr_fixup_test7 - ftr_fixup_test7); + + check(memcmp(ftr_fixup_test7, ftr_fixup_test7_expected, size) == 0); +} + static void test_cpu_macros(void) { extern u8 ftr_fixup_test_FTR_macros[]; @@ -480,6 +490,7 @@ static int __init test_feature_fixups(void) test_alternative_case_too_small(); test_alternative_case_with_branch(); test_alternative_case_with_external_branch(); + test_alternative_case_with_branch_to_end(); test_cpu_macros(); test_fw_macros(); test_lwsync_macros(); diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c index 34d68f1b1b40..49427a3ee104 100644 --- a/arch/powerpc/lib/sstep.c +++ b/arch/powerpc/lib/sstep.c @@ -1065,9 +1065,10 @@ static nokprobe_inline void do_popcnt(const struct pt_regs *regs, { unsigned long long out = v1; - out -= (out >> 1) & 0x5555555555555555; - out = (0x3333333333333333 & out) + (0x3333333333333333 & (out >> 2)); - out = (out + (out >> 4)) & 0x0f0f0f0f0f0f0f0f; + out -= (out >> 1) & 0x5555555555555555ULL; + out = (0x3333333333333333ULL & out) + + (0x3333333333333333ULL & (out >> 2)); + out = (out + (out >> 4)) & 0x0f0f0f0f0f0f0f0fULL; if (size == 8) { /* popcntb */ op->val = out; @@ -1076,7 +1077,7 @@ static nokprobe_inline void do_popcnt(const struct pt_regs *regs, out += out >> 8; out += out >> 16; if (size == 32) { /* popcntw */ - op->val = out & 0x0000003f0000003f; + op->val = out & 0x0000003f0000003fULL; return; } @@ -1114,7 +1115,7 @@ static nokprobe_inline void do_prty(const struct pt_regs *regs, res ^= res >> 16; if (size == 32) { /* prtyw */ - op->val = res & 0x0000000100000001; + op->val = res & 0x0000000100000001ULL; return; } diff --git a/arch/powerpc/lib/xor_vmx_glue.c b/arch/powerpc/lib/xor_vmx_glue.c index 6521fe5e8cef..dab2b6bfcf36 100644 --- a/arch/powerpc/lib/xor_vmx_glue.c +++ b/arch/powerpc/lib/xor_vmx_glue.c @@ -13,6 +13,7 @@ #include <linux/export.h> #include <linux/sched.h> #include <asm/switch_to.h> +#include <asm/xor_altivec.h> #include "xor_vmx.h" void xor_altivec_2(unsigned long bytes, unsigned long *v1_in, diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index c01d627e687a..3fafacd3f907 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -22,6 +22,7 @@ #include <linux/errno.h> #include <linux/string.h> #include <linux/types.h> +#include <linux/pagemap.h> #include <linux/ptrace.h> #include <linux/mman.h> #include <linux/mm.h> @@ -66,37 +67,33 @@ static inline bool notify_page_fault(struct pt_regs *regs) } /* - * Check whether the instruction at regs->nip is a store using + * Check whether the instruction inst is a store using * an update addressing form which will update r1. */ -static bool store_updates_sp(struct pt_regs *regs) +static bool store_updates_sp(unsigned int inst) { - unsigned int inst; - - if (get_user(inst, (unsigned int __user *)regs->nip)) - return false; /* check for 1 in the rA field */ if (((inst >> 16) & 0x1f) != 1) return false; /* check major opcode */ switch (inst >> 26) { - case 37: /* stwu */ - case 39: /* stbu */ - case 45: /* sthu */ - case 53: /* stfsu */ - case 55: /* stfdu */ + case OP_STWU: + case OP_STBU: + case OP_STHU: + case OP_STFSU: + case OP_STFDU: return true; - case 62: /* std or stdu */ + case OP_STD: /* std or stdu */ return (inst & 3) == 1; - case 31: + case OP_31: /* check minor opcode */ switch ((inst >> 1) & 0x3ff) { - case 181: /* stdux */ - case 183: /* stwux */ - case 247: /* stbux */ - case 439: /* sthux */ - case 695: /* stfsux */ - case 759: /* stfdux */ + case OP_31_XOP_STDUX: + case OP_31_XOP_STWUX: + case OP_31_XOP_STBUX: + case OP_31_XOP_STHUX: + case OP_31_XOP_STFSUX: + case OP_31_XOP_STFDUX: return true; } } @@ -234,8 +231,8 @@ static bool bad_kernel_fault(bool is_exec, unsigned long error_code, } static bool bad_stack_expansion(struct pt_regs *regs, unsigned long address, - struct vm_area_struct *vma, - bool store_update_sp) + struct vm_area_struct *vma, unsigned int flags, + bool *must_retry) { /* * N.B. The POWER/Open ABI allows programs to access up to @@ -247,6 +244,7 @@ static bool bad_stack_expansion(struct pt_regs *regs, unsigned long address, * expand to 1MB without further checks. */ if (address + 0x100000 < vma->vm_end) { + unsigned int __user *nip = (unsigned int __user *)regs->nip; /* get user regs even if this fault is in kernel mode */ struct pt_regs *uregs = current->thread.regs; if (uregs == NULL) @@ -264,8 +262,22 @@ static bool bad_stack_expansion(struct pt_regs *regs, unsigned long address, * between the last mapped region and the stack will * expand the stack rather than segfaulting. */ - if (address + 2048 < uregs->gpr[1] && !store_update_sp) - return true; + if (address + 2048 >= uregs->gpr[1]) + return false; + + if ((flags & FAULT_FLAG_WRITE) && (flags & FAULT_FLAG_USER) && + access_ok(VERIFY_READ, nip, sizeof(*nip))) { + unsigned int inst; + int res; + + pagefault_disable(); + res = __get_user_inatomic(inst, nip); + pagefault_enable(); + if (!res) + return !store_updates_sp(inst); + *must_retry = true; + } + return true; } return false; } @@ -403,7 +415,7 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address, int is_user = user_mode(regs); int is_write = page_fault_is_write(error_code); int fault, major = 0; - bool store_update_sp = false; + bool must_retry = false; if (notify_page_fault(regs)) return 0; @@ -454,9 +466,6 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address, * can result in fault, which will cause a deadlock when called with * mmap_sem held */ - if (is_write && is_user) - store_update_sp = store_updates_sp(regs); - if (is_user) flags |= FAULT_FLAG_USER; if (is_write) @@ -503,8 +512,17 @@ retry: return bad_area(regs, address); /* The stack is being expanded, check if it's valid */ - if (unlikely(bad_stack_expansion(regs, address, vma, store_update_sp))) - return bad_area(regs, address); + if (unlikely(bad_stack_expansion(regs, address, vma, flags, + &must_retry))) { + if (!must_retry) + return bad_area(regs, address); + + up_read(&mm->mmap_sem); + if (fault_in_pages_readable((const char __user *)regs->nip, + sizeof(unsigned int))) + return bad_area_nosemaphore(regs, address); + goto retry; + } /* Try to expand it */ if (unlikely(expand_stack(vma, address))) diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index 0bd3790d35df..8318716e5075 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -64,6 +64,7 @@ #include <asm/trace.h> #include <asm/ps3.h> #include <asm/pte-walk.h> +#include <asm/asm-prototypes.h> #ifdef DEBUG #define DBG(fmt...) udbg_printf(fmt) @@ -572,8 +573,10 @@ static void __init htab_scan_page_sizes(void) } #ifdef CONFIG_HUGETLB_PAGE - /* Reserve 16G huge page memory sections for huge pages */ - of_scan_flat_dt(htab_dt_scan_hugepage_blocks, NULL); + if (!hugetlb_disabled) { + /* Reserve 16G huge page memory sections for huge pages */ + of_scan_flat_dt(htab_dt_scan_hugepage_blocks, NULL); + } #endif /* CONFIG_HUGETLB_PAGE */ } @@ -1010,13 +1013,14 @@ void __init hash__early_init_mmu(void) */ __pte_frag_nr = H_PTE_FRAG_NR; __pte_frag_size_shift = H_PTE_FRAG_SIZE_SHIFT; + __pmd_frag_nr = H_PMD_FRAG_NR; + __pmd_frag_size_shift = H_PMD_FRAG_SIZE_SHIFT; __pte_index_size = H_PTE_INDEX_SIZE; __pmd_index_size = H_PMD_INDEX_SIZE; __pud_index_size = H_PUD_INDEX_SIZE; __pgd_index_size = H_PGD_INDEX_SIZE; __pud_cache_index = H_PUD_CACHE_INDEX; - __pmd_cache_index = H_PMD_CACHE_INDEX; __pte_table_size = H_PTE_TABLE_SIZE; __pmd_table_size = H_PMD_TABLE_SIZE; __pud_table_size = H_PUD_TABLE_SIZE; diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index f1153f8254e3..2a4b1bf8bde6 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -35,6 +35,8 @@ #define PAGE_SHIFT_16M 24 #define PAGE_SHIFT_16G 34 +bool hugetlb_disabled = false; + unsigned int HPAGE_SHIFT; EXPORT_SYMBOL(HPAGE_SHIFT); @@ -651,6 +653,11 @@ static int __init hugetlbpage_init(void) { int psize; + if (hugetlb_disabled) { + pr_info("HugeTLB support is disabled!\n"); + return 0; + } + #if !defined(CONFIG_PPC_FSL_BOOK3E) && !defined(CONFIG_PPC_8xx) if (!radix_enabled() && !mmu_has_feature(MMU_FTR_16M_PAGE)) return -ENODEV; diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/mmu_context_book3s64.c index b75194dff64c..f3d4b4a0e561 100644 --- a/arch/powerpc/mm/mmu_context_book3s64.c +++ b/arch/powerpc/mm/mmu_context_book3s64.c @@ -159,9 +159,8 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm) mm->context.id = index; -#ifdef CONFIG_PPC_64K_PAGES mm->context.pte_frag = NULL; -#endif + mm->context.pmd_frag = NULL; #ifdef CONFIG_SPAPR_TCE_IOMMU mm_iommu_init(mm); #endif @@ -192,17 +191,11 @@ static void destroy_contexts(mm_context_t *ctx) spin_unlock(&mmu_context_lock); } -#ifdef CONFIG_PPC_64K_PAGES -static void destroy_pagetable_page(struct mm_struct *mm) +static void pte_frag_destroy(void *pte_frag) { int count; - void *pte_frag; struct page *page; - pte_frag = mm->context.pte_frag; - if (!pte_frag) - return; - page = virt_to_page(pte_frag); /* drop all the pending references */ count = ((unsigned long)pte_frag & ~PAGE_MASK) >> PTE_FRAG_SIZE_SHIFT; @@ -213,12 +206,34 @@ static void destroy_pagetable_page(struct mm_struct *mm) } } -#else -static inline void destroy_pagetable_page(struct mm_struct *mm) +static void pmd_frag_destroy(void *pmd_frag) { + int count; + struct page *page; + + page = virt_to_page(pmd_frag); + /* drop all the pending references */ + count = ((unsigned long)pmd_frag & ~PAGE_MASK) >> PMD_FRAG_SIZE_SHIFT; + /* We allow PTE_FRAG_NR fragments from a PTE page */ + if (page_ref_sub_and_test(page, PMD_FRAG_NR - count)) { + pgtable_pmd_page_dtor(page); + free_unref_page(page); + } +} + +static void destroy_pagetable_page(struct mm_struct *mm) +{ + void *frag; + + frag = mm->context.pte_frag; + if (frag) + pte_frag_destroy(frag); + + frag = mm->context.pmd_frag; + if (frag) + pmd_frag_destroy(frag); return; } -#endif void destroy_context(struct mm_struct *mm) { diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c index 518518fb7c45..abda2b92f1ba 100644 --- a/arch/powerpc/mm/pgtable-book3s64.c +++ b/arch/powerpc/mm/pgtable-book3s64.c @@ -9,14 +9,22 @@ #include <linux/sched.h> #include <linux/mm_types.h> +#include <linux/memblock.h> #include <misc/cxl-base.h> #include <asm/pgalloc.h> #include <asm/tlb.h> +#include <asm/trace.h> +#include <asm/powernv.h> #include "mmu_decl.h" #include <trace/events/thp.h> +unsigned long __pmd_frag_nr; +EXPORT_SYMBOL(__pmd_frag_nr); +unsigned long __pmd_frag_size_shift; +EXPORT_SYMBOL(__pmd_frag_size_shift); + int (*register_process_table)(unsigned long base, unsigned long page_size, unsigned long tbl_size); @@ -34,7 +42,7 @@ int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, int changed; #ifdef CONFIG_DEBUG_VM WARN_ON(!pmd_trans_huge(*pmdp) && !pmd_devmap(*pmdp)); - assert_spin_locked(&vma->vm_mm->page_table_lock); + assert_spin_locked(pmd_lockptr(vma->vm_mm, pmdp)); #endif changed = !pmd_same(*(pmdp), entry); if (changed) { @@ -59,7 +67,7 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr, { #ifdef CONFIG_DEBUG_VM WARN_ON(pte_present(pmd_pte(*pmdp)) && !pte_protnone(pmd_pte(*pmdp))); - assert_spin_locked(&mm->page_table_lock); + assert_spin_locked(pmd_lockptr(mm, pmdp)); WARN_ON(!(pmd_trans_huge(pmd) || pmd_devmap(pmd))); #endif trace_hugepage_set_pmd(addr, pmd_val(pmd)); @@ -171,3 +179,258 @@ int __meminit remove_section_mapping(unsigned long start, unsigned long end) return hash__remove_section_mapping(start, end); } #endif /* CONFIG_MEMORY_HOTPLUG */ + +void __init mmu_partition_table_init(void) +{ + unsigned long patb_size = 1UL << PATB_SIZE_SHIFT; + unsigned long ptcr; + + BUILD_BUG_ON_MSG((PATB_SIZE_SHIFT > 36), "Partition table size too large."); + partition_tb = __va(memblock_alloc_base(patb_size, patb_size, + MEMBLOCK_ALLOC_ANYWHERE)); + + /* Initialize the Partition Table with no entries */ + memset((void *)partition_tb, 0, patb_size); + + /* + * update partition table control register, + * 64 K size. + */ + ptcr = __pa(partition_tb) | (PATB_SIZE_SHIFT - 12); + mtspr(SPRN_PTCR, ptcr); + powernv_set_nmmu_ptcr(ptcr); +} + +void mmu_partition_table_set_entry(unsigned int lpid, unsigned long dw0, + unsigned long dw1) +{ + unsigned long old = be64_to_cpu(partition_tb[lpid].patb0); + + partition_tb[lpid].patb0 = cpu_to_be64(dw0); + partition_tb[lpid].patb1 = cpu_to_be64(dw1); + + /* + * Global flush of TLBs and partition table caches for this lpid. + * The type of flush (hash or radix) depends on what the previous + * use of this partition ID was, not the new use. + */ + asm volatile("ptesync" : : : "memory"); + if (old & PATB_HR) { + asm volatile(PPC_TLBIE_5(%0,%1,2,0,1) : : + "r" (TLBIEL_INVAL_SET_LPID), "r" (lpid)); + asm volatile(PPC_TLBIE_5(%0,%1,2,1,1) : : + "r" (TLBIEL_INVAL_SET_LPID), "r" (lpid)); + trace_tlbie(lpid, 0, TLBIEL_INVAL_SET_LPID, lpid, 2, 0, 1); + } else { + asm volatile(PPC_TLBIE_5(%0,%1,2,0,0) : : + "r" (TLBIEL_INVAL_SET_LPID), "r" (lpid)); + trace_tlbie(lpid, 0, TLBIEL_INVAL_SET_LPID, lpid, 2, 0, 0); + } + /* do we need fixup here ?*/ + asm volatile("eieio; tlbsync; ptesync" : : : "memory"); +} +EXPORT_SYMBOL_GPL(mmu_partition_table_set_entry); + +static pmd_t *get_pmd_from_cache(struct mm_struct *mm) +{ + void *pmd_frag, *ret; + + spin_lock(&mm->page_table_lock); + ret = mm->context.pmd_frag; + if (ret) { + pmd_frag = ret + PMD_FRAG_SIZE; + /* + * If we have taken up all the fragments mark PTE page NULL + */ + if (((unsigned long)pmd_frag & ~PAGE_MASK) == 0) + pmd_frag = NULL; + mm->context.pmd_frag = pmd_frag; + } + spin_unlock(&mm->page_table_lock); + return (pmd_t *)ret; +} + +static pmd_t *__alloc_for_pmdcache(struct mm_struct *mm) +{ + void *ret = NULL; + struct page *page; + gfp_t gfp = GFP_KERNEL_ACCOUNT | __GFP_ZERO; + + if (mm == &init_mm) + gfp &= ~__GFP_ACCOUNT; + page = alloc_page(gfp); + if (!page) + return NULL; + if (!pgtable_pmd_page_ctor(page)) { + __free_pages(page, 0); + return NULL; + } + + ret = page_address(page); + /* + * if we support only one fragment just return the + * allocated page. + */ + if (PMD_FRAG_NR == 1) + return ret; + + spin_lock(&mm->page_table_lock); + /* + * If we find pgtable_page set, we return + * the allocated page with single fragement + * count. + */ + if (likely(!mm->context.pmd_frag)) { + set_page_count(page, PMD_FRAG_NR); + mm->context.pmd_frag = ret + PMD_FRAG_SIZE; + } + spin_unlock(&mm->page_table_lock); + + return (pmd_t *)ret; +} + +pmd_t *pmd_fragment_alloc(struct mm_struct *mm, unsigned long vmaddr) +{ + pmd_t *pmd; + + pmd = get_pmd_from_cache(mm); + if (pmd) + return pmd; + + return __alloc_for_pmdcache(mm); +} + +void pmd_fragment_free(unsigned long *pmd) +{ + struct page *page = virt_to_page(pmd); + + if (put_page_testzero(page)) { + pgtable_pmd_page_dtor(page); + free_unref_page(page); + } +} + +static pte_t *get_pte_from_cache(struct mm_struct *mm) +{ + void *pte_frag, *ret; + + spin_lock(&mm->page_table_lock); + ret = mm->context.pte_frag; + if (ret) { + pte_frag = ret + PTE_FRAG_SIZE; + /* + * If we have taken up all the fragments mark PTE page NULL + */ + if (((unsigned long)pte_frag & ~PAGE_MASK) == 0) + pte_frag = NULL; + mm->context.pte_frag = pte_frag; + } + spin_unlock(&mm->page_table_lock); + return (pte_t *)ret; +} + +static pte_t *__alloc_for_ptecache(struct mm_struct *mm, int kernel) +{ + void *ret = NULL; + struct page *page; + + if (!kernel) { + page = alloc_page(PGALLOC_GFP | __GFP_ACCOUNT); + if (!page) + return NULL; + if (!pgtable_page_ctor(page)) { + __free_page(page); + return NULL; + } + } else { + page = alloc_page(PGALLOC_GFP); + if (!page) + return NULL; + } + + + ret = page_address(page); + /* + * if we support only one fragment just return the + * allocated page. + */ + if (PTE_FRAG_NR == 1) + return ret; + spin_lock(&mm->page_table_lock); + /* + * If we find pgtable_page set, we return + * the allocated page with single fragement + * count. + */ + if (likely(!mm->context.pte_frag)) { + set_page_count(page, PTE_FRAG_NR); + mm->context.pte_frag = ret + PTE_FRAG_SIZE; + } + spin_unlock(&mm->page_table_lock); + + return (pte_t *)ret; +} + +pte_t *pte_fragment_alloc(struct mm_struct *mm, unsigned long vmaddr, int kernel) +{ + pte_t *pte; + + pte = get_pte_from_cache(mm); + if (pte) + return pte; + + return __alloc_for_ptecache(mm, kernel); +} + +void pte_fragment_free(unsigned long *table, int kernel) +{ + struct page *page = virt_to_page(table); + + if (put_page_testzero(page)) { + if (!kernel) + pgtable_page_dtor(page); + free_unref_page(page); + } +} + +static inline void pgtable_free(void *table, int index) +{ + switch (index) { + case PTE_INDEX: + pte_fragment_free(table, 0); + break; + case PMD_INDEX: + pmd_fragment_free(table); + break; + case PUD_INDEX: + kmem_cache_free(PGT_CACHE(PUD_CACHE_INDEX), table); + break; + /* We don't free pgd table via RCU callback */ + default: + BUG(); + } +} + +#ifdef CONFIG_SMP +void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int index) +{ + unsigned long pgf = (unsigned long)table; + + BUG_ON(index > MAX_PGTABLE_INDEX_SIZE); + pgf |= index; + tlb_remove_table(tlb, (void *)pgf); +} + +void __tlb_remove_table(void *_table) +{ + void *table = (void *)((unsigned long)_table & ~MAX_PGTABLE_INDEX_SIZE); + unsigned int index = (unsigned long)_table & MAX_PGTABLE_INDEX_SIZE; + + return pgtable_free(table, index); +} +#else +void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int index) +{ + return pgtable_free(table, index); +} +#endif diff --git a/arch/powerpc/mm/pgtable-hash64.c b/arch/powerpc/mm/pgtable-hash64.c index 199bfda5f0d9..692bfc9e372c 100644 --- a/arch/powerpc/mm/pgtable-hash64.c +++ b/arch/powerpc/mm/pgtable-hash64.c @@ -193,7 +193,7 @@ unsigned long hash__pmd_hugepage_update(struct mm_struct *mm, unsigned long addr #ifdef CONFIG_DEBUG_VM WARN_ON(!hash__pmd_trans_huge(*pmdp) && !pmd_devmap(*pmdp)); - assert_spin_locked(&mm->page_table_lock); + assert_spin_locked(pmd_lockptr(mm, pmdp)); #endif __asm__ __volatile__( @@ -265,7 +265,8 @@ void hash__pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, pgtable_t pgtable) { pgtable_t *pgtable_slot; - assert_spin_locked(&mm->page_table_lock); + + assert_spin_locked(pmd_lockptr(mm, pmdp)); /* * we store the pgtable in the second half of PMD */ @@ -285,7 +286,8 @@ pgtable_t hash__pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp) pgtable_t pgtable; pgtable_t *pgtable_slot; - assert_spin_locked(&mm->page_table_lock); + assert_spin_locked(pmd_lockptr(mm, pmdp)); + pgtable_slot = (pgtable_t *)pmdp + PTRS_PER_PMD; pgtable = *pgtable_slot; /* diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index f1891e215e39..ce24d72ea679 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -617,7 +617,6 @@ void __init radix__early_init_mmu(void) __pud_index_size = RADIX_PUD_INDEX_SIZE; __pgd_index_size = RADIX_PGD_INDEX_SIZE; __pud_cache_index = RADIX_PUD_INDEX_SIZE; - __pmd_cache_index = RADIX_PMD_INDEX_SIZE; __pte_table_size = RADIX_PTE_TABLE_SIZE; __pmd_table_size = RADIX_PMD_TABLE_SIZE; __pud_table_size = RADIX_PUD_TABLE_SIZE; @@ -640,6 +639,8 @@ void __init radix__early_init_mmu(void) #endif __pte_frag_nr = RADIX_PTE_FRAG_NR; __pte_frag_size_shift = RADIX_PTE_FRAG_SIZE_SHIFT; + __pmd_frag_nr = RADIX_PMD_FRAG_NR; + __pmd_frag_size_shift = RADIX_PMD_FRAG_SIZE_SHIFT; if (!firmware_has_feature(FW_FEATURE_LPAR)) { radix_init_native(); @@ -975,7 +976,7 @@ unsigned long radix__pmd_hugepage_update(struct mm_struct *mm, unsigned long add #ifdef CONFIG_DEBUG_VM WARN_ON(!radix__pmd_trans_huge(*pmdp) && !pmd_devmap(*pmdp)); - assert_spin_locked(&mm->page_table_lock); + assert_spin_locked(pmd_lockptr(mm, pmdp)); #endif old = radix__pte_update(mm, addr, (pte_t *)pmdp, clr, set, 1); diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index 9bf659d5078c..53e9eeecd5d4 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -33,7 +33,6 @@ #include <linux/swap.h> #include <linux/stddef.h> #include <linux/vmalloc.h> -#include <linux/memblock.h> #include <linux/slab.h> #include <linux/hugetlb.h> @@ -47,13 +46,11 @@ #include <asm/smp.h> #include <asm/machdep.h> #include <asm/tlb.h> -#include <asm/trace.h> #include <asm/processor.h> #include <asm/cputable.h> #include <asm/sections.h> #include <asm/firmware.h> #include <asm/dma.h> -#include <asm/powernv.h> #include "mmu_decl.h" @@ -75,8 +72,6 @@ unsigned long __pud_index_size; EXPORT_SYMBOL(__pud_index_size); unsigned long __pgd_index_size; EXPORT_SYMBOL(__pgd_index_size); -unsigned long __pmd_cache_index; -EXPORT_SYMBOL(__pmd_cache_index); unsigned long __pud_cache_index; EXPORT_SYMBOL(__pud_cache_index); unsigned long __pte_table_size; @@ -316,172 +311,6 @@ struct page *pmd_page(pmd_t pmd) return virt_to_page(pmd_page_vaddr(pmd)); } -#ifdef CONFIG_PPC_64K_PAGES -static pte_t *get_from_cache(struct mm_struct *mm) -{ - void *pte_frag, *ret; - - spin_lock(&mm->page_table_lock); - ret = mm->context.pte_frag; - if (ret) { - pte_frag = ret + PTE_FRAG_SIZE; - /* - * If we have taken up all the fragments mark PTE page NULL - */ - if (((unsigned long)pte_frag & ~PAGE_MASK) == 0) - pte_frag = NULL; - mm->context.pte_frag = pte_frag; - } - spin_unlock(&mm->page_table_lock); - return (pte_t *)ret; -} - -static pte_t *__alloc_for_cache(struct mm_struct *mm, int kernel) -{ - void *ret = NULL; - struct page *page; - - if (!kernel) { - page = alloc_page(PGALLOC_GFP | __GFP_ACCOUNT); - if (!page) - return NULL; - if (!pgtable_page_ctor(page)) { - __free_page(page); - return NULL; - } - } else { - page = alloc_page(PGALLOC_GFP); - if (!page) - return NULL; - } - - ret = page_address(page); - spin_lock(&mm->page_table_lock); - /* - * If we find pgtable_page set, we return - * the allocated page with single fragement - * count. - */ - if (likely(!mm->context.pte_frag)) { - set_page_count(page, PTE_FRAG_NR); - mm->context.pte_frag = ret + PTE_FRAG_SIZE; - } - spin_unlock(&mm->page_table_lock); - - return (pte_t *)ret; -} - -pte_t *pte_fragment_alloc(struct mm_struct *mm, unsigned long vmaddr, int kernel) -{ - pte_t *pte; - - pte = get_from_cache(mm); - if (pte) - return pte; - - return __alloc_for_cache(mm, kernel); -} -#endif /* CONFIG_PPC_64K_PAGES */ - -void pte_fragment_free(unsigned long *table, int kernel) -{ - struct page *page = virt_to_page(table); - if (put_page_testzero(page)) { - if (!kernel) - pgtable_page_dtor(page); - free_unref_page(page); - } -} - -#ifdef CONFIG_SMP -void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift) -{ - unsigned long pgf = (unsigned long)table; - - BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE); - pgf |= shift; - tlb_remove_table(tlb, (void *)pgf); -} - -void __tlb_remove_table(void *_table) -{ - void *table = (void *)((unsigned long)_table & ~MAX_PGTABLE_INDEX_SIZE); - unsigned shift = (unsigned long)_table & MAX_PGTABLE_INDEX_SIZE; - - if (!shift) - /* PTE page needs special handling */ - pte_fragment_free(table, 0); - else { - BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE); - kmem_cache_free(PGT_CACHE(shift), table); - } -} -#else -void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift) -{ - if (!shift) { - /* PTE page needs special handling */ - pte_fragment_free(table, 0); - } else { - BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE); - kmem_cache_free(PGT_CACHE(shift), table); - } -} -#endif - -#ifdef CONFIG_PPC_BOOK3S_64 -void __init mmu_partition_table_init(void) -{ - unsigned long patb_size = 1UL << PATB_SIZE_SHIFT; - unsigned long ptcr; - - BUILD_BUG_ON_MSG((PATB_SIZE_SHIFT > 36), "Partition table size too large."); - partition_tb = __va(memblock_alloc_base(patb_size, patb_size, - MEMBLOCK_ALLOC_ANYWHERE)); - - /* Initialize the Partition Table with no entries */ - memset((void *)partition_tb, 0, patb_size); - - /* - * update partition table control register, - * 64 K size. - */ - ptcr = __pa(partition_tb) | (PATB_SIZE_SHIFT - 12); - mtspr(SPRN_PTCR, ptcr); - powernv_set_nmmu_ptcr(ptcr); -} - -void mmu_partition_table_set_entry(unsigned int lpid, unsigned long dw0, - unsigned long dw1) -{ - unsigned long old = be64_to_cpu(partition_tb[lpid].patb0); - - partition_tb[lpid].patb0 = cpu_to_be64(dw0); - partition_tb[lpid].patb1 = cpu_to_be64(dw1); - - /* - * Global flush of TLBs and partition table caches for this lpid. - * The type of flush (hash or radix) depends on what the previous - * use of this partition ID was, not the new use. - */ - asm volatile("ptesync" : : : "memory"); - if (old & PATB_HR) { - asm volatile(PPC_TLBIE_5(%0,%1,2,0,1) : : - "r" (TLBIEL_INVAL_SET_LPID), "r" (lpid)); - asm volatile(PPC_TLBIE_5(%0,%1,2,1,1) : : - "r" (TLBIEL_INVAL_SET_LPID), "r" (lpid)); - trace_tlbie(lpid, 0, TLBIEL_INVAL_SET_LPID, lpid, 2, 0, 1); - } else { - asm volatile(PPC_TLBIE_5(%0,%1,2,0,0) : : - "r" (TLBIEL_INVAL_SET_LPID), "r" (lpid)); - trace_tlbie(lpid, 0, TLBIEL_INVAL_SET_LPID, lpid, 2, 0, 0); - } - /* do we need fixup here ?*/ - asm volatile("eieio; tlbsync; ptesync" : : : "memory"); -} -EXPORT_SYMBOL_GPL(mmu_partition_table_set_entry); -#endif /* CONFIG_PPC_BOOK3S_64 */ - #ifdef CONFIG_STRICT_KERNEL_RWX void mark_rodata_ro(void) { diff --git a/arch/powerpc/mm/ppc_mmu_32.c b/arch/powerpc/mm/ppc_mmu_32.c index 2a049fb8523d..bea6c544e38f 100644 --- a/arch/powerpc/mm/ppc_mmu_32.c +++ b/arch/powerpc/mm/ppc_mmu_32.c @@ -167,7 +167,7 @@ void hash_preload(struct mm_struct *mm, unsigned long ea, { pmd_t *pmd; - if (Hash == 0) + if (!Hash) return; pmd = pmd_offset(pud_offset(pgd_offset(mm, ea), ea), ea); if (!pmd_none(*pmd)) diff --git a/arch/powerpc/mm/subpage-prot.c b/arch/powerpc/mm/subpage-prot.c index f14a07c2fb90..9d16ee251fc0 100644 --- a/arch/powerpc/mm/subpage-prot.c +++ b/arch/powerpc/mm/subpage-prot.c @@ -13,6 +13,7 @@ #include <linux/types.h> #include <linux/mm.h> #include <linux/hugetlb.h> +#include <linux/syscalls.h> #include <asm/pgtable.h> #include <linux/uaccess.h> @@ -185,7 +186,8 @@ static void subpage_mark_vma_nohuge(struct mm_struct *mm, unsigned long addr, * in a 2-bit field won't allow writes to a page that is otherwise * write-protected. */ -long sys_subpage_prot(unsigned long addr, unsigned long len, u32 __user *map) +SYSCALL_DEFINE3(subpage_prot, unsigned long, addr, + unsigned long, len, u32 __user *, map) { struct mm_struct *mm = current->mm; struct subpage_prot_table *spt = &mm->context.spt; diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c index a5d7309c2d05..5ac3206c51cc 100644 --- a/arch/powerpc/mm/tlb-radix.c +++ b/arch/powerpc/mm/tlb-radix.c @@ -118,6 +118,53 @@ static inline void __tlbie_pid(unsigned long pid, unsigned long ric) trace_tlbie(0, 0, rb, rs, ric, prs, r); } +static inline void __tlbiel_lpid(unsigned long lpid, int set, + unsigned long ric) +{ + unsigned long rb,rs,prs,r; + + rb = PPC_BIT(52); /* IS = 2 */ + rb |= set << PPC_BITLSHIFT(51); + rs = 0; /* LPID comes from LPIDR */ + prs = 0; /* partition scoped */ + r = 1; /* radix format */ + + asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1) + : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory"); + trace_tlbie(lpid, 1, rb, rs, ric, prs, r); +} + +static inline void __tlbie_lpid(unsigned long lpid, unsigned long ric) +{ + unsigned long rb,rs,prs,r; + + rb = PPC_BIT(52); /* IS = 2 */ + rs = lpid; + prs = 0; /* partition scoped */ + r = 1; /* radix format */ + + asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1) + : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory"); + trace_tlbie(lpid, 0, rb, rs, ric, prs, r); +} + +static inline void __tlbiel_lpid_guest(unsigned long lpid, int set, + unsigned long ric) +{ + unsigned long rb,rs,prs,r; + + rb = PPC_BIT(52); /* IS = 2 */ + rb |= set << PPC_BITLSHIFT(51); + rs = 0; /* LPID comes from LPIDR */ + prs = 1; /* process scoped */ + r = 1; /* radix format */ + + asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1) + : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory"); + trace_tlbie(lpid, 1, rb, rs, ric, prs, r); +} + + static inline void __tlbiel_va(unsigned long va, unsigned long pid, unsigned long ap, unsigned long ric) { @@ -150,6 +197,22 @@ static inline void __tlbie_va(unsigned long va, unsigned long pid, trace_tlbie(0, 0, rb, rs, ric, prs, r); } +static inline void __tlbie_lpid_va(unsigned long va, unsigned long lpid, + unsigned long ap, unsigned long ric) +{ + unsigned long rb,rs,prs,r; + + rb = va & ~(PPC_BITMASK(52, 63)); + rb |= ap << PPC_BITLSHIFT(58); + rs = lpid; + prs = 0; /* partition scoped */ + r = 1; /* radix format */ + + asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1) + : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory"); + trace_tlbie(lpid, 0, rb, rs, ric, prs, r); +} + static inline void fixup_tlbie(void) { unsigned long pid = 0; @@ -161,6 +224,16 @@ static inline void fixup_tlbie(void) } } +static inline void fixup_tlbie_lpid(unsigned long lpid) +{ + unsigned long va = ((1UL << 52) - 1); + + if (cpu_has_feature(CPU_FTR_P9_TLBIE_BUG)) { + asm volatile("ptesync": : :"memory"); + __tlbie_lpid_va(va, lpid, mmu_get_ap(MMU_PAGE_64K), RIC_FLUSH_TLB); + } +} + /* * We use 128 set in radix mode and 256 set in hpt mode. */ @@ -214,6 +287,86 @@ static inline void _tlbie_pid(unsigned long pid, unsigned long ric) asm volatile("eieio; tlbsync; ptesync": : :"memory"); } +static inline void _tlbiel_lpid(unsigned long lpid, unsigned long ric) +{ + int set; + + VM_BUG_ON(mfspr(SPRN_LPID) != lpid); + + asm volatile("ptesync": : :"memory"); + + /* + * Flush the first set of the TLB, and if we're doing a RIC_FLUSH_ALL, + * also flush the entire Page Walk Cache. + */ + __tlbiel_lpid(lpid, 0, ric); + + /* For PWC, only one flush is needed */ + if (ric == RIC_FLUSH_PWC) { + asm volatile("ptesync": : :"memory"); + return; + } + + /* For the remaining sets, just flush the TLB */ + for (set = 1; set < POWER9_TLB_SETS_RADIX ; set++) + __tlbiel_lpid(lpid, set, RIC_FLUSH_TLB); + + asm volatile("ptesync": : :"memory"); + asm volatile(PPC_INVALIDATE_ERAT "; isync" : : :"memory"); +} + +static inline void _tlbie_lpid(unsigned long lpid, unsigned long ric) +{ + asm volatile("ptesync": : :"memory"); + + /* + * Workaround the fact that the "ric" argument to __tlbie_pid + * must be a compile-time contraint to match the "i" constraint + * in the asm statement. + */ + switch (ric) { + case RIC_FLUSH_TLB: + __tlbie_lpid(lpid, RIC_FLUSH_TLB); + break; + case RIC_FLUSH_PWC: + __tlbie_lpid(lpid, RIC_FLUSH_PWC); + break; + case RIC_FLUSH_ALL: + default: + __tlbie_lpid(lpid, RIC_FLUSH_ALL); + } + fixup_tlbie_lpid(lpid); + asm volatile("eieio; tlbsync; ptesync": : :"memory"); +} + +static inline void _tlbiel_lpid_guest(unsigned long lpid, unsigned long ric) +{ + int set; + + VM_BUG_ON(mfspr(SPRN_LPID) != lpid); + + asm volatile("ptesync": : :"memory"); + + /* + * Flush the first set of the TLB, and if we're doing a RIC_FLUSH_ALL, + * also flush the entire Page Walk Cache. + */ + __tlbiel_lpid_guest(lpid, 0, ric); + + /* For PWC, only one flush is needed */ + if (ric == RIC_FLUSH_PWC) { + asm volatile("ptesync": : :"memory"); + return; + } + + /* For the remaining sets, just flush the TLB */ + for (set = 1; set < POWER9_TLB_SETS_RADIX ; set++) + __tlbiel_lpid_guest(lpid, set, RIC_FLUSH_TLB); + + asm volatile("ptesync": : :"memory"); +} + + static inline void __tlbiel_va_range(unsigned long start, unsigned long end, unsigned long pid, unsigned long page_size, unsigned long psize) @@ -268,6 +421,17 @@ static inline void _tlbie_va(unsigned long va, unsigned long pid, asm volatile("eieio; tlbsync; ptesync": : :"memory"); } +static inline void _tlbie_lpid_va(unsigned long va, unsigned long lpid, + unsigned long psize, unsigned long ric) +{ + unsigned long ap = mmu_get_ap(psize); + + asm volatile("ptesync": : :"memory"); + __tlbie_lpid_va(va, lpid, ap, ric); + fixup_tlbie_lpid(lpid); + asm volatile("eieio; tlbsync; ptesync": : :"memory"); +} + static inline void _tlbie_va_range(unsigned long start, unsigned long end, unsigned long pid, unsigned long page_size, unsigned long psize, bool also_pwc) @@ -534,6 +698,49 @@ static int radix_get_mmu_psize(int page_size) return psize; } +/* + * Flush partition scoped LPID address translation for all CPUs. + */ +void radix__flush_tlb_lpid_page(unsigned int lpid, + unsigned long addr, + unsigned long page_size) +{ + int psize = radix_get_mmu_psize(page_size); + + _tlbie_lpid_va(addr, lpid, psize, RIC_FLUSH_TLB); +} +EXPORT_SYMBOL_GPL(radix__flush_tlb_lpid_page); + +/* + * Flush partition scoped PWC from LPID for all CPUs. + */ +void radix__flush_pwc_lpid(unsigned int lpid) +{ + _tlbie_lpid(lpid, RIC_FLUSH_PWC); +} +EXPORT_SYMBOL_GPL(radix__flush_pwc_lpid); + +/* + * Flush partition scoped translations from LPID (=LPIDR) + */ +void radix__local_flush_tlb_lpid(unsigned int lpid) +{ + _tlbiel_lpid(lpid, RIC_FLUSH_ALL); +} +EXPORT_SYMBOL_GPL(radix__local_flush_tlb_lpid); + +/* + * Flush process scoped translations from LPID (=LPIDR). + * Important difference, the guest normally manages its own translations, + * but some cases e.g., vCPU CPU migration require KVM to flush. + */ +void radix__local_flush_tlb_lpid_guest(unsigned int lpid) +{ + _tlbiel_lpid_guest(lpid, RIC_FLUSH_ALL); +} +EXPORT_SYMBOL_GPL(radix__local_flush_tlb_lpid_guest); + + static void radix__flush_tlb_pwc_range_psize(struct mm_struct *mm, unsigned long start, unsigned long end, int psize); diff --git a/arch/powerpc/mm/tlb_hash32.c b/arch/powerpc/mm/tlb_hash32.c index 702d7689d714..cf8472cf3d59 100644 --- a/arch/powerpc/mm/tlb_hash32.c +++ b/arch/powerpc/mm/tlb_hash32.c @@ -41,7 +41,7 @@ void flush_hash_entry(struct mm_struct *mm, pte_t *ptep, unsigned long addr) { unsigned long ptephys; - if (Hash != 0) { + if (Hash) { ptephys = __pa(ptep) & PAGE_MASK; flush_hash_pages(mm->context.id, addr, ptephys, 1); } @@ -54,7 +54,7 @@ EXPORT_SYMBOL(flush_hash_entry); */ void tlb_flush(struct mmu_gather *tlb) { - if (Hash == 0) { + if (!Hash) { /* * 603 needs to flush the whole TLB here since * it doesn't use a hash table. @@ -84,7 +84,7 @@ static void flush_range(struct mm_struct *mm, unsigned long start, int count; unsigned int ctx = mm->context.id; - if (Hash == 0) { + if (!Hash) { _tlbia(); return; } @@ -124,7 +124,7 @@ void flush_tlb_mm(struct mm_struct *mm) { struct vm_area_struct *mp; - if (Hash == 0) { + if (!Hash) { _tlbia(); return; } @@ -145,7 +145,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr) struct mm_struct *mm; pmd_t *pmd; - if (Hash == 0) { + if (!Hash) { _tlbie(vmaddr); return; } diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c index d7532e7b9ab5..75fb23c24ee8 100644 --- a/arch/powerpc/perf/imc-pmu.c +++ b/arch/powerpc/perf/imc-pmu.c @@ -1146,7 +1146,7 @@ static int init_nest_pmu_ref(void) static void cleanup_all_core_imc_memory(void) { - int i, nr_cores = DIV_ROUND_UP(num_present_cpus(), threads_per_core); + int i, nr_cores = DIV_ROUND_UP(num_possible_cpus(), threads_per_core); struct imc_mem_info *ptr = core_imc_pmu->mem_info; int size = core_imc_pmu->counter_mem_size; @@ -1264,7 +1264,7 @@ static int imc_mem_init(struct imc_pmu *pmu_ptr, struct device_node *parent, if (!pmu_ptr->pmu.name) return -ENOMEM; - nr_cores = DIV_ROUND_UP(num_present_cpus(), threads_per_core); + nr_cores = DIV_ROUND_UP(num_possible_cpus(), threads_per_core); pmu_ptr->mem_info = kcalloc(nr_cores, sizeof(struct imc_mem_info), GFP_KERNEL); diff --git a/arch/powerpc/perf/isa207-common.h b/arch/powerpc/perf/isa207-common.h index 6c737d675792..6a0b586c935a 100644 --- a/arch/powerpc/perf/isa207-common.h +++ b/arch/powerpc/perf/isa207-common.h @@ -17,70 +17,6 @@ #include <asm/firmware.h> #include <asm/cputable.h> -/* - * Raw event encoding for PowerISA v2.07: - * - * 60 56 52 48 44 40 36 32 - * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - * | | [ ] [ thresh_cmp ] [ thresh_ctl ] - * | | | | - * | | *- IFM (Linux) thresh start/stop OR FAB match -* - * | *- BHRB (Linux) - * *- EBB (Linux) - * - * 28 24 20 16 12 8 4 0 - * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - * [ ] [ sample ] [cache] [ pmc ] [unit ] c m [ pmcxsel ] - * | | | | | - * | | | | *- mark - * | | *- L1/L2/L3 cache_sel | - * | | | - * | *- sampling mode for marked events *- combine - * | - * *- thresh_sel - * - * Below uses IBM bit numbering. - * - * MMCR1[x:y] = unit (PMCxUNIT) - * MMCR1[x] = combine (PMCxCOMB) - * - * if pmc == 3 and unit == 0 and pmcxsel[0:6] == 0b0101011 - * # PM_MRK_FAB_RSP_MATCH - * MMCR1[20:27] = thresh_ctl (FAB_CRESP_MATCH / FAB_TYPE_MATCH) - * else if pmc == 4 and unit == 0xf and pmcxsel[0:6] == 0b0101001 - * # PM_MRK_FAB_RSP_MATCH_CYC - * MMCR1[20:27] = thresh_ctl (FAB_CRESP_MATCH / FAB_TYPE_MATCH) - * else - * MMCRA[48:55] = thresh_ctl (THRESH START/END) - * - * if thresh_sel: - * MMCRA[45:47] = thresh_sel - * - * if thresh_cmp: - * MMCRA[22:24] = thresh_cmp[0:2] - * MMCRA[25:31] = thresh_cmp[3:9] - * - * if unit == 6 or unit == 7 - * MMCRC[53:55] = cache_sel[1:3] (L2EVENT_SEL) - * else if unit == 8 or unit == 9: - * if cache_sel[0] == 0: # L3 bank - * MMCRC[47:49] = cache_sel[1:3] (L3EVENT_SEL0) - * else if cache_sel[0] == 1: - * MMCRC[50:51] = cache_sel[2:3] (L3EVENT_SEL1) - * else if cache_sel[1]: # L1 event - * MMCR1[16] = cache_sel[2] -Â * MMCR1[17] = cache_sel[3] - * - * if mark: - * MMCRA[63] = 1 (SAMPLE_ENABLE) - * MMCRA[57:59] = sample[0:2] (RAND_SAMP_ELIG) -Â * MMCRA[61:62] = sample[3:4] (RAND_SAMP_MODE) - * - * if EBB and BHRB: - * MMCRA[32:33] = IFM - * - */ - #define EVENT_EBB_MASK 1ull #define EVENT_EBB_SHIFT PERF_EVENT_CONFIG_EBB_SHIFT #define EVENT_BHRB_MASK 1ull diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c index c9356955cab4..d12a2db26353 100644 --- a/arch/powerpc/perf/power8-pmu.c +++ b/arch/powerpc/perf/power8-pmu.c @@ -30,6 +30,70 @@ enum { #define POWER8_MMCRA_IFM2 0x0000000080000000UL #define POWER8_MMCRA_IFM3 0x00000000C0000000UL +/* + * Raw event encoding for PowerISA v2.07 (Power8): + * + * 60 56 52 48 44 40 36 32 + * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | + * | | [ ] [ thresh_cmp ] [ thresh_ctl ] + * | | | | + * | | *- IFM (Linux) thresh start/stop OR FAB match -* + * | *- BHRB (Linux) + * *- EBB (Linux) + * + * 28 24 20 16 12 8 4 0 + * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | + * [ ] [ sample ] [cache] [ pmc ] [unit ] c m [ pmcxsel ] + * | | | | | + * | | | | *- mark + * | | *- L1/L2/L3 cache_sel | + * | | | + * | *- sampling mode for marked events *- combine + * | + * *- thresh_sel + * + * Below uses IBM bit numbering. + * + * MMCR1[x:y] = unit (PMCxUNIT) + * MMCR1[x] = combine (PMCxCOMB) + * + * if pmc == 3 and unit == 0 and pmcxsel[0:6] == 0b0101011 + * # PM_MRK_FAB_RSP_MATCH + * MMCR1[20:27] = thresh_ctl (FAB_CRESP_MATCH / FAB_TYPE_MATCH) + * else if pmc == 4 and unit == 0xf and pmcxsel[0:6] == 0b0101001 + * # PM_MRK_FAB_RSP_MATCH_CYC + * MMCR1[20:27] = thresh_ctl (FAB_CRESP_MATCH / FAB_TYPE_MATCH) + * else + * MMCRA[48:55] = thresh_ctl (THRESH START/END) + * + * if thresh_sel: + * MMCRA[45:47] = thresh_sel + * + * if thresh_cmp: + * MMCRA[22:24] = thresh_cmp[0:2] + * MMCRA[25:31] = thresh_cmp[3:9] + * + * if unit == 6 or unit == 7 + * MMCRC[53:55] = cache_sel[1:3] (L2EVENT_SEL) + * else if unit == 8 or unit == 9: + * if cache_sel[0] == 0: # L3 bank + * MMCRC[47:49] = cache_sel[1:3] (L3EVENT_SEL0) + * else if cache_sel[0] == 1: + * MMCRC[50:51] = cache_sel[2:3] (L3EVENT_SEL1) + * else if cache_sel[1]: # L1 event + * MMCR1[16] = cache_sel[2] +Â * MMCR1[17] = cache_sel[3] + * + * if mark: + * MMCRA[63] = 1 (SAMPLE_ENABLE) + * MMCRA[57:59] = sample[0:2] (RAND_SAMP_ELIG) +Â * MMCRA[61:62] = sample[3:4] (RAND_SAMP_MODE) + * + * if EBB and BHRB: + * MMCRA[32:33] = IFM + * + */ + /* PowerISA v2.07 format attribute structure*/ extern struct attribute_group isa207_pmu_format_group; diff --git a/arch/powerpc/platforms/83xx/Kconfig b/arch/powerpc/platforms/83xx/Kconfig index 7e38b7b71a5a..071f53b0c0a0 100644 --- a/arch/powerpc/platforms/83xx/Kconfig +++ b/arch/powerpc/platforms/83xx/Kconfig @@ -90,13 +90,6 @@ config MPC837x_RDB help This option enables support for the MPC837x RDB and WLAN Boards. -config SBC834x - bool "Wind River SBC834x" - select DEFAULT_UIMAGE - select PPC_MPC834x - help - This option enables support for the Wind River SBC834x board. - config ASP834x bool "Analogue & Micro ASP 834x" select PPC_MPC834x diff --git a/arch/powerpc/platforms/83xx/Makefile b/arch/powerpc/platforms/83xx/Makefile index bb4720897f6a..41cb5f842eff 100644 --- a/arch/powerpc/platforms/83xx/Makefile +++ b/arch/powerpc/platforms/83xx/Makefile @@ -14,7 +14,6 @@ obj-$(CONFIG_MPC836x_MDS) += mpc836x_mds.o obj-$(CONFIG_MPC836x_RDK) += mpc836x_rdk.o obj-$(CONFIG_MPC832x_MDS) += mpc832x_mds.o obj-$(CONFIG_MPC837x_MDS) += mpc837x_mds.o -obj-$(CONFIG_SBC834x) += sbc834x.o obj-$(CONFIG_MPC837x_RDB) += mpc837x_rdb.o obj-$(CONFIG_ASP834x) += asp834x.o obj-$(CONFIG_KMETER1) += km83xx.o diff --git a/arch/powerpc/platforms/83xx/sbc834x.c b/arch/powerpc/platforms/83xx/sbc834x.c deleted file mode 100644 index cb4bdabfdf1c..000000000000 --- a/arch/powerpc/platforms/83xx/sbc834x.c +++ /dev/null @@ -1,73 +0,0 @@ -/* - * arch/powerpc/platforms/83xx/sbc834x.c - * - * Wind River SBC834x board specific routines - * - * By Paul Gortmaker (see MAINTAINERS for contact information) - * - * Based largely on the mpc834x_mds.c support by Kumar Gala. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - */ - -#include <linux/stddef.h> -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/errno.h> -#include <linux/reboot.h> -#include <linux/pci.h> -#include <linux/kdev_t.h> -#include <linux/major.h> -#include <linux/console.h> -#include <linux/delay.h> -#include <linux/seq_file.h> -#include <linux/root_dev.h> -#include <linux/of_platform.h> - -#include <linux/atomic.h> -#include <asm/time.h> -#include <asm/io.h> -#include <asm/machdep.h> -#include <asm/ipic.h> -#include <asm/irq.h> -#include <asm/prom.h> -#include <asm/udbg.h> -#include <sysdev/fsl_soc.h> -#include <sysdev/fsl_pci.h> - -#include "mpc83xx.h" - -/* ************************************************************************ - * - * Setup the architecture - * - */ -static void __init sbc834x_setup_arch(void) -{ - mpc83xx_setup_arch(); -} - -machine_device_initcall(sbc834x, mpc83xx_declare_of_platform_devices); - -/* - * Called very early, MMU is off, device-tree isn't unflattened - */ -static int __init sbc834x_probe(void) -{ - return of_machine_is_compatible("SBC834xE"); -} - -define_machine(sbc834x) { - .name = "SBC834xE", - .probe = sbc834x_probe, - .setup_arch = sbc834x_setup_arch, - .init_IRQ = mpc83xx_ipic_init_IRQ, - .get_irq = ipic_get_irq, - .restart = mpc83xx_restart, - .time_init = mpc83xx_time_init, - .calibrate_decr = generic_calibrate_decr, - .progress = udbg_progress, -}; diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index 67d3125d0610..cc892dcfa114 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -292,6 +292,10 @@ config PPC_STD_MMU_32 def_bool y depends on PPC_STD_MMU && PPC32 +config ARCH_ENABLE_SPLIT_PMD_PTLOCK + def_bool y + depends on PPC_BOOK3S_64 + config PPC_RADIX_MMU bool "Radix MMU Support" depends on PPC_BOOK3S_64 diff --git a/arch/powerpc/platforms/cell/spu_callbacks.c b/arch/powerpc/platforms/cell/spu_callbacks.c index a494028b2cdf..8ae86200ef6c 100644 --- a/arch/powerpc/platforms/cell/spu_callbacks.c +++ b/arch/powerpc/platforms/cell/spu_callbacks.c @@ -44,7 +44,7 @@ static void *spu_syscall_table[] = { #define SYSCALL_SPU(func) sys_##func, #define COMPAT_SYS_SPU(func) sys_##func, -#define PPC_SYS_SPU(func) ppc_##func, +#define COMPAT_SPU_NEW(func) sys_##func, #define SYSX_SPU(f, f3264, f32) f, #include <asm/systbl.h> diff --git a/arch/powerpc/platforms/cell/spu_syscalls.c b/arch/powerpc/platforms/cell/spu_syscalls.c index 5e6e0bad6db6..263413a34823 100644 --- a/arch/powerpc/platforms/cell/spu_syscalls.c +++ b/arch/powerpc/platforms/cell/spu_syscalls.c @@ -26,6 +26,7 @@ #include <linux/syscalls.h> #include <linux/rcupdate.h> #include <linux/binfmts.h> +#include <linux/syscalls.h> #include <asm/spu.h> @@ -90,7 +91,7 @@ SYSCALL_DEFINE4(spu_create, const char __user *, name, unsigned int, flags, return ret; } -asmlinkage long sys_spu_run(int fd, __u32 __user *unpc, __u32 __user *ustatus) +SYSCALL_DEFINE3(spu_run,int, fd, __u32 __user *, unpc, __u32 __user *, ustatus) { long ret; struct fd arg; diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c index 469bdd0b748f..43e7b93f27c7 100644 --- a/arch/powerpc/platforms/cell/spufs/file.c +++ b/arch/powerpc/platforms/cell/spufs/file.c @@ -232,12 +232,13 @@ spufs_mem_write(struct file *file, const char __user *buffer, return size; } -static int +static vm_fault_t spufs_mem_mmap_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct spu_context *ctx = vma->vm_file->private_data; unsigned long pfn, offset; + vm_fault_t ret; offset = vmf->pgoff << PAGE_SHIFT; if (offset >= LS_SIZE) @@ -256,11 +257,11 @@ spufs_mem_mmap_fault(struct vm_fault *vmf) vma->vm_page_prot = pgprot_noncached_wc(vma->vm_page_prot); pfn = (ctx->spu->local_store_phys + offset) >> PAGE_SHIFT; } - vm_insert_pfn(vma, vmf->address, pfn); + ret = vmf_insert_pfn(vma, vmf->address, pfn); spu_release(ctx); - return VM_FAULT_NOPAGE; + return ret; } static int spufs_mem_mmap_access(struct vm_area_struct *vma, @@ -312,13 +313,14 @@ static const struct file_operations spufs_mem_fops = { .mmap = spufs_mem_mmap, }; -static int spufs_ps_fault(struct vm_fault *vmf, +static vm_fault_t spufs_ps_fault(struct vm_fault *vmf, unsigned long ps_offs, unsigned long ps_size) { struct spu_context *ctx = vmf->vma->vm_file->private_data; unsigned long area, offset = vmf->pgoff << PAGE_SHIFT; - int ret = 0; + int err = 0; + vm_fault_t ret = VM_FAULT_NOPAGE; spu_context_nospu_trace(spufs_ps_fault__enter, ctx); @@ -349,25 +351,26 @@ static int spufs_ps_fault(struct vm_fault *vmf, if (ctx->state == SPU_STATE_SAVED) { up_read(¤t->mm->mmap_sem); spu_context_nospu_trace(spufs_ps_fault__sleep, ctx); - ret = spufs_wait(ctx->run_wq, ctx->state == SPU_STATE_RUNNABLE); + err = spufs_wait(ctx->run_wq, ctx->state == SPU_STATE_RUNNABLE); spu_context_trace(spufs_ps_fault__wake, ctx, ctx->spu); down_read(¤t->mm->mmap_sem); } else { area = ctx->spu->problem_phys + ps_offs; - vm_insert_pfn(vmf->vma, vmf->address, (area + offset) >> PAGE_SHIFT); + ret = vmf_insert_pfn(vmf->vma, vmf->address, + (area + offset) >> PAGE_SHIFT); spu_context_trace(spufs_ps_fault__insert, ctx, ctx->spu); } - if (!ret) + if (!err) spu_release(ctx); refault: put_spu_context(ctx); - return VM_FAULT_NOPAGE; + return ret; } #if SPUFS_MMAP_4K -static int spufs_cntl_mmap_fault(struct vm_fault *vmf) +static vm_fault_t spufs_cntl_mmap_fault(struct vm_fault *vmf) { return spufs_ps_fault(vmf, 0x4000, SPUFS_CNTL_MAP_SIZE); } @@ -1040,7 +1043,7 @@ static ssize_t spufs_signal1_write(struct file *file, const char __user *buf, return 4; } -static int +static vm_fault_t spufs_signal1_mmap_fault(struct vm_fault *vmf) { #if SPUFS_SIGNAL_MAP_SIZE == 0x1000 @@ -1178,7 +1181,7 @@ static ssize_t spufs_signal2_write(struct file *file, const char __user *buf, } #if SPUFS_MMAP_4K -static int +static vm_fault_t spufs_signal2_mmap_fault(struct vm_fault *vmf) { #if SPUFS_SIGNAL_MAP_SIZE == 0x1000 @@ -1307,7 +1310,7 @@ DEFINE_SPUFS_ATTRIBUTE(spufs_signal2_type, spufs_signal2_type_get, spufs_signal2_type_set, "%llu\n", SPU_ATTR_ACQUIRE); #if SPUFS_MMAP_4K -static int +static vm_fault_t spufs_mss_mmap_fault(struct vm_fault *vmf) { return spufs_ps_fault(vmf, 0x0000, SPUFS_MSS_MAP_SIZE); @@ -1369,7 +1372,7 @@ static const struct file_operations spufs_mss_fops = { .llseek = no_llseek, }; -static int +static vm_fault_t spufs_psmap_mmap_fault(struct vm_fault *vmf) { return spufs_ps_fault(vmf, 0x0000, SPUFS_PS_MAP_SIZE); @@ -1429,7 +1432,7 @@ static const struct file_operations spufs_psmap_fops = { #if SPUFS_MMAP_4K -static int +static vm_fault_t spufs_mfc_mmap_fault(struct vm_fault *vmf) { return spufs_ps_fault(vmf, 0x3000, SPUFS_MFC_MAP_SIZE); diff --git a/arch/powerpc/platforms/chrp/pci.c b/arch/powerpc/platforms/chrp/pci.c index 0f512d35f7c5..5ddb57b82921 100644 --- a/arch/powerpc/platforms/chrp/pci.c +++ b/arch/powerpc/platforms/chrp/pci.c @@ -31,7 +31,7 @@ void __iomem *gg2_pci_config_base; * limit the bus number to 3 bits */ -int gg2_read_config(struct pci_bus *bus, unsigned int devfn, int off, +static int gg2_read_config(struct pci_bus *bus, unsigned int devfn, int off, int len, u32 *val) { volatile void __iomem *cfg_data; @@ -58,7 +58,7 @@ int gg2_read_config(struct pci_bus *bus, unsigned int devfn, int off, return PCIBIOS_SUCCESSFUL; } -int gg2_write_config(struct pci_bus *bus, unsigned int devfn, int off, +static int gg2_write_config(struct pci_bus *bus, unsigned int devfn, int off, int len, u32 val) { volatile void __iomem *cfg_data; @@ -94,8 +94,8 @@ static struct pci_ops gg2_pci_ops = /* * Access functions for PCI config space using RTAS calls. */ -int rtas_read_config(struct pci_bus *bus, unsigned int devfn, int offset, - int len, u32 *val) +static int rtas_read_config(struct pci_bus *bus, unsigned int devfn, int offset, + int len, u32 *val) { struct pci_controller *hose = pci_bus_to_host(bus); unsigned long addr = (offset & 0xff) | ((devfn & 0xff) << 8) @@ -109,8 +109,8 @@ int rtas_read_config(struct pci_bus *bus, unsigned int devfn, int offset, return rval? PCIBIOS_DEVICE_NOT_FOUND: PCIBIOS_SUCCESSFUL; } -int rtas_write_config(struct pci_bus *bus, unsigned int devfn, int offset, - int len, u32 val) +static int rtas_write_config(struct pci_bus *bus, unsigned int devfn, int offset, + int len, u32 val) { struct pci_controller *hose = pci_bus_to_host(bus); unsigned long addr = (offset & 0xff) | ((devfn & 0xff) << 8) diff --git a/arch/powerpc/platforms/chrp/setup.c b/arch/powerpc/platforms/chrp/setup.c index 481ed133e04b..d6d8ffc0271e 100644 --- a/arch/powerpc/platforms/chrp/setup.c +++ b/arch/powerpc/platforms/chrp/setup.c @@ -94,7 +94,7 @@ static const char *chrp_names[] = { "Total Impact Briq" }; -void chrp_show_cpuinfo(struct seq_file *m) +static void chrp_show_cpuinfo(struct seq_file *m) { int i, sdramen; unsigned int t; @@ -299,7 +299,7 @@ out_put: of_node_put(node); } -void __init chrp_setup_arch(void) +static void __init chrp_setup_arch(void) { struct device_node *root = of_find_node_by_path("/"); const char *machine = NULL; @@ -382,7 +382,7 @@ static void __init chrp_find_openpic(void) { struct device_node *np, *root; int len, i, j; - int isu_size, idu_size; + int isu_size; const unsigned int *iranges, *opprop = NULL; int oplen = 0; unsigned long opaddr; @@ -427,11 +427,9 @@ static void __init chrp_find_openpic(void) } isu_size = 0; - idu_size = 0; if (len > 0 && iranges[1] != 0) { printk(KERN_INFO "OpenPIC irqs %d..%d in IDU\n", iranges[0], iranges[0] + iranges[1] - 1); - idu_size = iranges[1]; } if (len > 1) isu_size = iranges[3]; @@ -523,7 +521,7 @@ static void __init chrp_find_8259(void) } } -void __init chrp_init_IRQ(void) +static void __init chrp_init_IRQ(void) { #if defined(CONFIG_VT) && defined(CONFIG_INPUT_ADBHID) && defined(CONFIG_XMON) struct device_node *kbd; @@ -555,7 +553,7 @@ void __init chrp_init_IRQ(void) #endif } -void __init +static void __init chrp_init2(void) { #ifdef CONFIG_NVRAM diff --git a/arch/powerpc/platforms/chrp/time.c b/arch/powerpc/platforms/chrp/time.c index 03d115aaa191..acde7bbe0716 100644 --- a/arch/powerpc/platforms/chrp/time.c +++ b/arch/powerpc/platforms/chrp/time.c @@ -28,6 +28,8 @@ #include <asm/sections.h> #include <asm/time.h> +#include <platforms/chrp/chrp.h> + extern spinlock_t rtc_lock; #define NVRAM_AS0 0x74 @@ -63,7 +65,7 @@ long __init chrp_time_init(void) return 0; } -int chrp_cmos_clock_read(int addr) +static int chrp_cmos_clock_read(int addr) { if (nvram_as1 != 0) outb(addr>>8, nvram_as1); @@ -71,7 +73,7 @@ int chrp_cmos_clock_read(int addr) return (inb(nvram_data)); } -void chrp_cmos_clock_write(unsigned long val, int addr) +static void chrp_cmos_clock_write(unsigned long val, int addr) { if (nvram_as1 != 0) outb(addr>>8, nvram_as1); diff --git a/arch/powerpc/platforms/embedded6xx/flipper-pic.c b/arch/powerpc/platforms/embedded6xx/flipper-pic.c index 7206f3f573d4..db0be007fd06 100644 --- a/arch/powerpc/platforms/embedded6xx/flipper-pic.c +++ b/arch/powerpc/platforms/embedded6xx/flipper-pic.c @@ -108,16 +108,8 @@ static int flipper_pic_map(struct irq_domain *h, unsigned int virq, return 0; } -static int flipper_pic_match(struct irq_domain *h, struct device_node *np, - enum irq_domain_bus_token bus_token) -{ - return 1; -} - - static const struct irq_domain_ops flipper_irq_domain_ops = { .map = flipper_pic_map, - .match = flipper_pic_match, }; /* diff --git a/arch/powerpc/platforms/embedded6xx/hlwd-pic.c b/arch/powerpc/platforms/embedded6xx/hlwd-pic.c index 89c54de88b7a..8112b39879d6 100644 --- a/arch/powerpc/platforms/embedded6xx/hlwd-pic.c +++ b/arch/powerpc/platforms/embedded6xx/hlwd-pic.c @@ -35,6 +35,8 @@ */ #define HW_BROADWAY_ICR 0x00 #define HW_BROADWAY_IMR 0x04 +#define HW_STARLET_ICR 0x08 +#define HW_STARLET_IMR 0x0c /* @@ -74,6 +76,9 @@ static void hlwd_pic_unmask(struct irq_data *d) void __iomem *io_base = irq_data_get_irq_chip_data(d); setbits32(io_base + HW_BROADWAY_IMR, 1 << irq); + + /* Make sure the ARM (aka. Starlet) doesn't handle this interrupt. */ + clrbits32(io_base + HW_STARLET_IMR, 1 << irq); } @@ -155,7 +160,7 @@ static void __hlwd_quiesce(void __iomem *io_base) out_be32(io_base + HW_BROADWAY_ICR, 0xffffffff); } -struct irq_domain *hlwd_pic_init(struct device_node *np) +static struct irq_domain *hlwd_pic_init(struct device_node *np) { struct irq_domain *irq_domain; struct resource res; diff --git a/arch/powerpc/platforms/powermac/bootx_init.c b/arch/powerpc/platforms/powermac/bootx_init.c index c3c9bbb3573a..ba0964c17620 100644 --- a/arch/powerpc/platforms/powermac/bootx_init.c +++ b/arch/powerpc/platforms/powermac/bootx_init.c @@ -468,7 +468,7 @@ void __init bootx_init(unsigned long r3, unsigned long r4) boot_infos_t *bi = (boot_infos_t *) r4; unsigned long hdr; unsigned long space; - unsigned long ptr, x; + unsigned long ptr; char *model; unsigned long offset = reloc_offset(); @@ -562,6 +562,8 @@ void __init bootx_init(unsigned long r3, unsigned long r4) * MMU switched OFF, so this should not be useful anymore. */ if (bi->version < 4) { + unsigned long x __maybe_unused; + bootx_printf("Touching pages...\n"); /* diff --git a/arch/powerpc/platforms/powermac/pci.c b/arch/powerpc/platforms/powermac/pci.c index 0b8174a79993..df762bb3c735 100644 --- a/arch/powerpc/platforms/powermac/pci.c +++ b/arch/powerpc/platforms/powermac/pci.c @@ -62,7 +62,7 @@ struct device_node *k2_skiplist[2]; static int __init fixup_one_level_bus_range(struct device_node *node, int higher) { - for (; node != 0;node = node->sibling) { + for (; node; node = node->sibling) { const int * bus_range; const unsigned int *class_code; int len; @@ -1219,7 +1219,7 @@ static void fixup_u4_pcie(struct pci_dev* dev) region = r; } /* Nothing found, bail */ - if (region == 0) + if (!region) return; /* Print things out */ diff --git a/arch/powerpc/platforms/powermac/setup.c b/arch/powerpc/platforms/powermac/setup.c index ab668cb72263..3a529fcdae97 100644 --- a/arch/powerpc/platforms/powermac/setup.c +++ b/arch/powerpc/platforms/powermac/setup.c @@ -152,7 +152,7 @@ static void pmac_show_cpuinfo(struct seq_file *m) of_get_property(np, "d-cache-size", NULL); seq_printf(m, "L2 cache\t:"); has_l2cache = 1; - if (of_get_property(np, "cache-unified", NULL) != 0 && dc) { + if (of_get_property(np, "cache-unified", NULL) && dc) { seq_printf(m, " %dK unified", *dc / 1024); } else { if (ic) @@ -244,12 +244,12 @@ static void __init l2cr_init(void) /* Checks "l2cr-value" property in the registry */ if (cpu_has_feature(CPU_FTR_L2CR)) { struct device_node *np = of_find_node_by_name(NULL, "cpus"); - if (np == 0) + if (!np) np = of_find_node_by_type(NULL, "cpu"); - if (np != 0) { + if (np) { const unsigned int *l2cr = of_get_property(np, "l2cr-value", NULL); - if (l2cr != 0) { + if (l2cr) { ppc_override_l2cr = 1; ppc_override_l2cr_value = *l2cr; _set_L2CR(0); @@ -352,6 +352,7 @@ static int pmac_late_init(void) } machine_late_initcall(powermac, pmac_late_init); +void note_bootable_part(dev_t dev, int part, int goodness); /* * This is __ref because we check for "initializing" before * touching any of the __init sensitive things and "initializing" diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c index 95275e0e2efa..447da6db450a 100644 --- a/arch/powerpc/platforms/powermac/smp.c +++ b/arch/powerpc/platforms/powermac/smp.c @@ -65,7 +65,6 @@ #endif extern void __secondary_start_pmac_0(void); -extern int pmac_pfunc_base_install(void); static void (*pmac_tb_freeze)(int freeze); static u64 timebase; diff --git a/arch/powerpc/platforms/powernv/copy-paste.h b/arch/powerpc/platforms/powernv/copy-paste.h index c9a503623431..3fa62de96d9c 100644 --- a/arch/powerpc/platforms/powernv/copy-paste.h +++ b/arch/powerpc/platforms/powernv/copy-paste.h @@ -7,9 +7,8 @@ * 2 of the License, or (at your option) any later version. */ #include <asm/ppc-opcode.h> +#include <asm/reg.h> -#define CR0_SHIFT 28 -#define CR0_MASK 0xF /* * Copy/paste instructions: * diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c index 1f12ab1e6030..1c5d0675b43c 100644 --- a/arch/powerpc/platforms/powernv/idle.c +++ b/arch/powerpc/platforms/powernv/idle.c @@ -79,7 +79,7 @@ static int pnv_save_sprs_for_deep_states(void) uint64_t msr_val = MSR_IDLE; uint64_t psscr_val = pnv_deepest_stop_psscr_val; - for_each_possible_cpu(cpu) { + for_each_present_cpu(cpu) { uint64_t pir = get_hard_smp_processor_id(cpu); uint64_t hsprg0_val = (uint64_t)paca_ptrs[cpu]; @@ -814,7 +814,7 @@ static int __init pnv_init_idle_states(void) int cpu; pr_info("powernv: idle: Saving PACA pointers of all CPUs in their thread sibling PACA\n"); - for_each_possible_cpu(cpu) { + for_each_present_cpu(cpu) { int base_cpu = cpu_first_thread_sibling(cpu); int idx = cpu_thread_in_core(cpu); int i; diff --git a/arch/powerpc/platforms/powernv/memtrace.c b/arch/powerpc/platforms/powernv/memtrace.c index fc222a0c2ac4..b99283df8584 100644 --- a/arch/powerpc/platforms/powernv/memtrace.c +++ b/arch/powerpc/platforms/powernv/memtrace.c @@ -131,7 +131,7 @@ static u64 memtrace_alloc_node(u32 nid, u64 size) u64 start_pfn, end_pfn, nr_pages; u64 base_pfn; - if (!NODE_DATA(nid) || !node_spanned_pages(nid)) + if (!node_spanned_pages(nid)) return 0; start_pfn = node_start_pfn(nid); diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c index 525e966dce34..8cdf91f5d3a4 100644 --- a/arch/powerpc/platforms/powernv/npu-dma.c +++ b/arch/powerpc/platforms/powernv/npu-dma.c @@ -459,10 +459,9 @@ static void mmio_launch_invalidate(struct mmio_atsd_reg *mmio_atsd_reg, struct npu *npu = mmio_atsd_reg->npu; int reg = mmio_atsd_reg->reg; - __raw_writeq(cpu_to_be64(va), - npu->mmio_atsd_regs[reg] + XTS_ATSD_AVA); + __raw_writeq_be(va, npu->mmio_atsd_regs[reg] + XTS_ATSD_AVA); eieio(); - __raw_writeq(cpu_to_be64(launch), npu->mmio_atsd_regs[reg]); + __raw_writeq_be(launch, npu->mmio_atsd_regs[reg]); } static void mmio_invalidate_pid(struct mmio_atsd_reg mmio_atsd_reg[NV_MAX_NPUS], diff --git a/arch/powerpc/platforms/powernv/opal-irqchip.c b/arch/powerpc/platforms/powernv/opal-irqchip.c index 9d1b8c0aaf93..05ffe05f0fdc 100644 --- a/arch/powerpc/platforms/powernv/opal-irqchip.c +++ b/arch/powerpc/platforms/powernv/opal-irqchip.c @@ -177,7 +177,7 @@ void opal_event_shutdown(void) if (!opal_irqs[i]) continue; - if (in_interrupt()) + if (in_interrupt() || irqs_disabled()) disable_irq_nosync(opal_irqs[i]); else free_irq(opal_irqs[i], NULL); diff --git a/arch/powerpc/platforms/powernv/opal-sensor.c b/arch/powerpc/platforms/powernv/opal-sensor.c index 0a7074bb91dc..35a5f4b9aeb5 100644 --- a/arch/powerpc/platforms/powernv/opal-sensor.c +++ b/arch/powerpc/platforms/powernv/opal-sensor.c @@ -72,6 +72,59 @@ out: } EXPORT_SYMBOL_GPL(opal_get_sensor_data); +int opal_get_sensor_data_u64(u32 sensor_hndl, u64 *sensor_data) +{ + int ret, token; + struct opal_msg msg; + __be64 data; + + if (!opal_check_token(OPAL_SENSOR_READ_U64)) { + u32 sdata; + + ret = opal_get_sensor_data(sensor_hndl, &sdata); + if (!ret) + *sensor_data = sdata; + return ret; + } + + token = opal_async_get_token_interruptible(); + if (token < 0) + return token; + + ret = opal_sensor_read_u64(sensor_hndl, token, &data); + switch (ret) { + case OPAL_ASYNC_COMPLETION: + ret = opal_async_wait_response(token, &msg); + if (ret) { + pr_err("%s: Failed to wait for the async response, %d\n", + __func__, ret); + goto out_token; + } + + ret = opal_error_code(opal_get_async_rc(msg)); + *sensor_data = be64_to_cpu(data); + break; + + case OPAL_SUCCESS: + ret = 0; + *sensor_data = be64_to_cpu(data); + break; + + case OPAL_WRONG_STATE: + ret = -EIO; + break; + + default: + ret = opal_error_code(ret); + break; + } + +out_token: + opal_async_release_token(token); + return ret; +} +EXPORT_SYMBOL_GPL(opal_get_sensor_data_u64); + int __init opal_sensor_init(void) { struct platform_device *pdev; diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S index 3da30c2f26b4..8482df255969 100644 --- a/arch/powerpc/platforms/powernv/opal-wrappers.S +++ b/arch/powerpc/platforms/powernv/opal-wrappers.S @@ -325,3 +325,4 @@ OPAL_CALL(opal_npu_spa_clear_cache, OPAL_NPU_SPA_CLEAR_CACHE); OPAL_CALL(opal_npu_tl_set, OPAL_NPU_TL_SET); OPAL_CALL(opal_pci_get_pbcq_tunnel_bar, OPAL_PCI_GET_PBCQ_TUNNEL_BAR); OPAL_CALL(opal_pci_set_pbcq_tunnel_bar, OPAL_PCI_SET_PBCQ_TUNNEL_BAR); +OPAL_CALL(opal_sensor_read_u64, OPAL_SENSOR_READ_U64); diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 3f9c69d7623a..1b02f86dfec1 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -1976,9 +1976,10 @@ static void pnv_pci_p7ioc_tce_invalidate(struct iommu_table *tbl, mb(); /* Ensure above stores are visible */ while (start <= end) { if (rm) - __raw_rm_writeq(cpu_to_be64(start), invalidate); + __raw_rm_writeq_be(start, invalidate); else - __raw_writeq(cpu_to_be64(start), invalidate); + __raw_writeq_be(start, invalidate); + start += inc; } @@ -2055,9 +2056,9 @@ static void pnv_pci_phb3_tce_invalidate_entire(struct pnv_phb *phb, bool rm) mb(); /* Ensure previous TCE table stores are visible */ if (rm) - __raw_rm_writeq(cpu_to_be64(val), invalidate); + __raw_rm_writeq_be(val, invalidate); else - __raw_writeq(cpu_to_be64(val), invalidate); + __raw_writeq_be(val, invalidate); } static inline void pnv_pci_phb3_tce_invalidate_pe(struct pnv_ioda_pe *pe) @@ -2067,7 +2068,7 @@ static inline void pnv_pci_phb3_tce_invalidate_pe(struct pnv_ioda_pe *pe) unsigned long val = PHB3_TCE_KILL_INVAL_PE | (pe->pe_number & 0xFF); mb(); /* Ensure above stores are visible */ - __raw_writeq(cpu_to_be64(val), invalidate); + __raw_writeq_be(val, invalidate); } static void pnv_pci_phb3_tce_invalidate(struct pnv_ioda_pe *pe, bool rm, @@ -2090,9 +2091,9 @@ static void pnv_pci_phb3_tce_invalidate(struct pnv_ioda_pe *pe, bool rm, while (start <= end) { if (rm) - __raw_rm_writeq(cpu_to_be64(start), invalidate); + __raw_rm_writeq_be(start, invalidate); else - __raw_writeq(cpu_to_be64(start), invalidate); + __raw_writeq_be(start, invalidate); start += inc; } } @@ -2910,6 +2911,34 @@ static void pnv_pci_ioda2_table_free_pages(struct iommu_table *tbl) tbl->it_indirect_levels); } +static unsigned long pnv_ioda_parse_tce_sizes(struct pnv_phb *phb) +{ + struct pci_controller *hose = phb->hose; + struct device_node *dn = hose->dn; + unsigned long mask = 0; + int i, rc, count; + u32 val; + + count = of_property_count_u32_elems(dn, "ibm,supported-tce-sizes"); + if (count <= 0) { + mask = SZ_4K | SZ_64K; + /* Add 16M for POWER8 by default */ + if (cpu_has_feature(CPU_FTR_ARCH_207S) && + !cpu_has_feature(CPU_FTR_ARCH_300)) + mask |= SZ_16M; + return mask; + } + + for (i = 0; i < count; i++) { + rc = of_property_read_u32_index(dn, "ibm,supported-tce-sizes", + i, &val); + if (rc == 0) + mask |= 1ULL << val; + } + + return mask; +} + static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe) { @@ -2934,7 +2963,7 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, pe->table_group.max_dynamic_windows_supported = IOMMU_TABLE_GROUP_MAX_TABLES; pe->table_group.max_levels = POWERNV_IOMMU_MAX_LEVELS; - pe->table_group.pgsizes = SZ_4K | SZ_64K | SZ_16M; + pe->table_group.pgsizes = pnv_ioda_parse_tce_sizes(phb); #ifdef CONFIG_IOMMU_API pe->table_group.ops = &pnv_pci_ioda2_ops; #endif diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index ef8c9ce53a61..fa63d3fff14c 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -356,15 +356,7 @@ static void pnv_kexec_cpu_down(int crash_shutdown, int secondary) #ifdef CONFIG_MEMORY_HOTPLUG_SPARSE static unsigned long pnv_memory_block_size(void) { - /* - * We map the kernel linear region with 1GB large pages on radix. For - * memory hot unplug to work our memory block size must be at least - * this size. - */ - if (radix_enabled()) - return 1UL * 1024 * 1024 * 1024; - else - return 256UL * 1024 * 1024; + return 256UL * 1024 * 1024; } #endif diff --git a/arch/powerpc/platforms/pseries/hvCall_inst.c b/arch/powerpc/platforms/pseries/hvCall_inst.c index 89b7ce807e70..6da320c786cd 100644 --- a/arch/powerpc/platforms/pseries/hvCall_inst.c +++ b/arch/powerpc/platforms/pseries/hvCall_inst.c @@ -125,7 +125,7 @@ static void probe_hcall_entry(void *ignored, unsigned long opcode, unsigned long h->purr_start = mfspr(SPRN_PURR); } -static void probe_hcall_exit(void *ignored, unsigned long opcode, unsigned long retval, +static void probe_hcall_exit(void *ignored, unsigned long opcode, long retval, unsigned long *retbuf) { struct hcall_stats *h; diff --git a/arch/powerpc/platforms/pseries/kexec.c b/arch/powerpc/platforms/pseries/kexec.c index 3fe126796975..46fbaef69a59 100644 --- a/arch/powerpc/platforms/pseries/kexec.c +++ b/arch/powerpc/platforms/pseries/kexec.c @@ -57,8 +57,11 @@ void pseries_kexec_cpu_down(int crash_shutdown, int secondary) } } - if (xive_enabled()) + if (xive_enabled()) { xive_kexec_teardown_cpu(secondary); - else + + if (!secondary) + xive_shutdown(); + } else xics_kexec_teardown_cpu(secondary); } diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index adb996ed51e1..5a392e40f3d2 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -902,8 +902,7 @@ out: local_irq_restore(flags); } -void __trace_hcall_exit(long opcode, unsigned long retval, - unsigned long *retbuf) +void __trace_hcall_exit(long opcode, long retval, unsigned long *retbuf) { unsigned long flags; unsigned int *depth; diff --git a/arch/powerpc/sysdev/xive/spapr.c b/arch/powerpc/sysdev/xive/spapr.c index 091f1d0d0af1..575db3b06a6b 100644 --- a/arch/powerpc/sysdev/xive/spapr.c +++ b/arch/powerpc/sysdev/xive/spapr.c @@ -19,6 +19,7 @@ #include <linux/spinlock.h> #include <linux/cpumask.h> #include <linux/mm.h> +#include <linux/delay.h> #include <asm/prom.h> #include <asm/io.h> @@ -108,6 +109,51 @@ static void xive_irq_bitmap_free(int irq) } } + +/* Based on the similar routines in RTAS */ +static unsigned int plpar_busy_delay_time(long rc) +{ + unsigned int ms = 0; + + if (H_IS_LONG_BUSY(rc)) { + ms = get_longbusy_msecs(rc); + } else if (rc == H_BUSY) { + ms = 10; /* seems appropriate for XIVE hcalls */ + } + + return ms; +} + +static unsigned int plpar_busy_delay(int rc) +{ + unsigned int ms; + + ms = plpar_busy_delay_time(rc); + if (ms) + mdelay(ms); + + return ms; +} + +/* + * Note: this call has a partition wide scope and can take a while to + * complete. If it returns H_LONG_BUSY_* it should be retried + * periodically. + */ +static long plpar_int_reset(unsigned long flags) +{ + long rc; + + do { + rc = plpar_hcall_norets(H_INT_RESET, flags); + } while (plpar_busy_delay(rc)); + + if (rc) + pr_err("H_INT_RESET failed %ld\n", rc); + + return rc; +} + static long plpar_int_get_source_info(unsigned long flags, unsigned long lisn, unsigned long *src_flags, @@ -118,7 +164,10 @@ static long plpar_int_get_source_info(unsigned long flags, unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; long rc; - rc = plpar_hcall(H_INT_GET_SOURCE_INFO, retbuf, flags, lisn); + do { + rc = plpar_hcall(H_INT_GET_SOURCE_INFO, retbuf, flags, lisn); + } while (plpar_busy_delay(rc)); + if (rc) { pr_err("H_INT_GET_SOURCE_INFO lisn=%ld failed %ld\n", lisn, rc); return rc; @@ -151,8 +200,11 @@ static long plpar_int_set_source_config(unsigned long flags, flags, lisn, target, prio, sw_irq); - rc = plpar_hcall_norets(H_INT_SET_SOURCE_CONFIG, flags, lisn, - target, prio, sw_irq); + do { + rc = plpar_hcall_norets(H_INT_SET_SOURCE_CONFIG, flags, lisn, + target, prio, sw_irq); + } while (plpar_busy_delay(rc)); + if (rc) { pr_err("H_INT_SET_SOURCE_CONFIG lisn=%ld target=%lx prio=%lx failed %ld\n", lisn, target, prio, rc); @@ -171,7 +223,11 @@ static long plpar_int_get_queue_info(unsigned long flags, unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; long rc; - rc = plpar_hcall(H_INT_GET_QUEUE_INFO, retbuf, flags, target, priority); + do { + rc = plpar_hcall(H_INT_GET_QUEUE_INFO, retbuf, flags, target, + priority); + } while (plpar_busy_delay(rc)); + if (rc) { pr_err("H_INT_GET_QUEUE_INFO cpu=%ld prio=%ld failed %ld\n", target, priority, rc); @@ -200,8 +256,11 @@ static long plpar_int_set_queue_config(unsigned long flags, pr_devel("H_INT_SET_QUEUE_CONFIG flags=%lx target=%lx priority=%lx qpage=%lx qsize=%lx\n", flags, target, priority, qpage, qsize); - rc = plpar_hcall_norets(H_INT_SET_QUEUE_CONFIG, flags, target, - priority, qpage, qsize); + do { + rc = plpar_hcall_norets(H_INT_SET_QUEUE_CONFIG, flags, target, + priority, qpage, qsize); + } while (plpar_busy_delay(rc)); + if (rc) { pr_err("H_INT_SET_QUEUE_CONFIG cpu=%ld prio=%ld qpage=%lx returned %ld\n", target, priority, qpage, rc); @@ -215,7 +274,10 @@ static long plpar_int_sync(unsigned long flags, unsigned long lisn) { long rc; - rc = plpar_hcall_norets(H_INT_SYNC, flags, lisn); + do { + rc = plpar_hcall_norets(H_INT_SYNC, flags, lisn); + } while (plpar_busy_delay(rc)); + if (rc) { pr_err("H_INT_SYNC lisn=%ld returned %ld\n", lisn, rc); return rc; @@ -238,7 +300,11 @@ static long plpar_int_esb(unsigned long flags, pr_devel("H_INT_ESB flags=%lx lisn=%lx offset=%lx in=%lx\n", flags, lisn, offset, in_data); - rc = plpar_hcall(H_INT_ESB, retbuf, flags, lisn, offset, in_data); + do { + rc = plpar_hcall(H_INT_ESB, retbuf, flags, lisn, offset, + in_data); + } while (plpar_busy_delay(rc)); + if (rc) { pr_err("H_INT_ESB lisn=%ld offset=%ld returned %ld\n", lisn, offset, rc); @@ -445,11 +511,7 @@ static void xive_spapr_put_ipi(unsigned int cpu, struct xive_cpu *xc) static void xive_spapr_shutdown(void) { - long rc; - - rc = plpar_hcall_norets(H_INT_RESET, 0); - if (rc) - pr_err("H_INT_RESET failed %ld\n", rc); + plpar_int_reset(0); } /* diff --git a/arch/powerpc/xmon/nonstdio.h b/arch/powerpc/xmon/nonstdio.h index 2202ec61972c..e8deac6c84e2 100644 --- a/arch/powerpc/xmon/nonstdio.h +++ b/arch/powerpc/xmon/nonstdio.h @@ -1,13 +1,13 @@ /* SPDX-License-Identifier: GPL-2.0 */ #define EOF (-1) -#define printf xmon_printf -#define putchar xmon_putchar - extern void xmon_set_pagination_lpp(unsigned long lpp); extern void xmon_start_pagination(void); extern void xmon_end_pagination(void); extern int xmon_putchar(int c); extern void xmon_puts(const char *); extern char *xmon_gets(char *, int); -extern void xmon_printf(const char *, ...); +extern __printf(1, 2) void xmon_printf(const char *fmt, ...); + +#define printf xmon_printf +#define putchar xmon_putchar diff --git a/arch/powerpc/xmon/spu-dis.c b/arch/powerpc/xmon/spu-dis.c index e5f89837c82e..4cbc7da88524 100644 --- a/arch/powerpc/xmon/spu-dis.c +++ b/arch/powerpc/xmon/spu-dis.c @@ -102,7 +102,7 @@ print_insn_spu (unsigned long insn, unsigned long memaddr) if (index == 0) { - printf(".long 0x%x", insn); + printf(".long 0x%lx", insn); } else { @@ -134,27 +134,27 @@ print_insn_spu (unsigned long insn, unsigned long memaddr) switch (arg) { case A_T: - printf("$%d", + printf("$%lu", DECODE_INSN_RT (insn)); break; case A_A: - printf("$%d", + printf("$%lu", DECODE_INSN_RA (insn)); break; case A_B: - printf("$%d", + printf("$%lu", DECODE_INSN_RB (insn)); break; case A_C: - printf("$%d", + printf("$%lu", DECODE_INSN_RC (insn)); break; case A_S: - printf("$sp%d", + printf("$sp%lu", DECODE_INSN_RA (insn)); break; case A_H: - printf("$ch%d", + printf("$ch%lu", DECODE_INSN_RA (insn)); break; case A_P: @@ -162,11 +162,11 @@ print_insn_spu (unsigned long insn, unsigned long memaddr) printf("("); break; case A_U7A: - printf("%d", + printf("%lu", 173 - DECODE_INSN_U8 (insn)); break; case A_U7B: - printf("%d", + printf("%lu", 155 - DECODE_INSN_U8 (insn)); break; case A_S3: diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index a0842f1ff72c..c2e9270728c7 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -515,7 +515,7 @@ static int xmon_core(struct pt_regs *regs, int fromipi) get_output_lock(); excprint(regs); if (bp) { - printf("cpu 0x%x stopped at breakpoint 0x%lx (", + printf("cpu 0x%x stopped at breakpoint 0x%tx (", cpu, BP_NUM(bp)); xmon_print_symbol(regs->nip, " ", ")\n"); } @@ -622,7 +622,7 @@ static int xmon_core(struct pt_regs *regs, int fromipi) excprint(regs); bp = at_breakpoint(regs->nip); if (bp) { - printf("Stopped at breakpoint %lx (", BP_NUM(bp)); + printf("Stopped at breakpoint %tx (", BP_NUM(bp)); xmon_print_symbol(regs->nip, " ", ")\n"); } if (unrecoverable_excp(regs)) @@ -778,6 +778,16 @@ static int xmon_fault_handler(struct pt_regs *regs) return 0; } +/* Force enable xmon if not already enabled */ +static inline void force_enable_xmon(void) +{ + /* Enable xmon hooks if needed */ + if (!xmon_on) { + printf("xmon: Enabling debugger hooks\n"); + xmon_on = 1; + } +} + static struct bpt *at_breakpoint(unsigned long pc) { int i; @@ -1094,6 +1104,7 @@ static int do_step(struct pt_regs *regs) unsigned int instr; int stepped; + force_enable_xmon(); /* check we are in 64-bit kernel mode, translation enabled */ if ((regs->msr & (MSR_64BIT|MSR_PR|MSR_IR)) == (MSR_64BIT|MSR_IR)) { if (mread(regs->nip, &instr, 4) == 4) { @@ -1160,7 +1171,7 @@ static int cpu_cmd(void) } /* try to switch to cpu specified */ if (!cpumask_test_cpu(cpu, &cpus_in_xmon)) { - printf("cpu 0x%x isn't in xmon\n", cpu); + printf("cpu 0x%lx isn't in xmon\n", cpu); return 0; } xmon_taken = 0; @@ -1174,7 +1185,7 @@ static int cpu_cmd(void) /* take control back */ mb(); xmon_owner = smp_processor_id(); - printf("cpu 0x%x didn't take control\n", cpu); + printf("cpu 0x%lx didn't take control\n", cpu); return 0; } barrier(); @@ -1268,16 +1279,6 @@ static long check_bp_loc(unsigned long addr) return 1; } -/* Force enable xmon if not already enabled */ -static inline void force_enable_xmon(void) -{ - /* Enable xmon hooks if needed */ - if (!xmon_on) { - printf("xmon: Enabling debugger hooks\n"); - xmon_on = 1; - } -} - static char *breakpoint_help_string = "Breakpoint command usage:\n" "b show breakpoints\n" @@ -1374,7 +1375,7 @@ bpt_cmds(void) } } - printf("Cleared breakpoint %lx (", BP_NUM(bp)); + printf("Cleared breakpoint %tx (", BP_NUM(bp)); xmon_print_symbol(bp->address, " ", ")\n"); bp->enabled = 0; break; @@ -1401,7 +1402,7 @@ bpt_cmds(void) for (bp = bpts; bp < &bpts[NBPTS]; ++bp) { if (!bp->enabled) continue; - printf("%2x %s ", BP_NUM(bp), + printf("%tx %s ", BP_NUM(bp), (bp->enabled & BP_CIABR) ? "inst": "trap"); xmon_print_symbol(bp->address, " ", "\n"); } @@ -1618,11 +1619,11 @@ static void excprint(struct pt_regs *fp) #endif /* CONFIG_SMP */ trap = TRAP(fp); - printf("Vector: %lx %s at [%lx]\n", fp->trap, getvecname(trap), fp); + printf("Vector: %lx %s at [%px]\n", fp->trap, getvecname(trap), fp); printf(" pc: "); xmon_print_symbol(fp->nip, ": ", "\n"); - printf(" lr: ", fp->link); + printf(" lr: "); xmon_print_symbol(fp->link, ": ", "\n"); printf(" sp: %lx\n", fp->gpr[1]); @@ -1634,13 +1635,13 @@ static void excprint(struct pt_regs *fp) printf(" dsisr: %lx\n", fp->dsisr); } - printf(" current = 0x%lx\n", current); + printf(" current = 0x%px\n", current); #ifdef CONFIG_PPC64 - printf(" paca = 0x%lx\t softe: %d\t irq_happened: 0x%02x\n", + printf(" paca = 0x%px\t softe: %d\t irq_happened: 0x%02x\n", local_paca, local_paca->irq_soft_mask, local_paca->irq_happened); #endif if (current) { - printf(" pid = %ld, comm = %s\n", + printf(" pid = %d, comm = %s\n", current->pid, current->comm); } @@ -1676,16 +1677,16 @@ static void prregs(struct pt_regs *fp) #ifdef CONFIG_PPC64 if (FULL_REGS(fp)) { for (n = 0; n < 16; ++n) - printf("R%.2ld = "REG" R%.2ld = "REG"\n", + printf("R%.2d = "REG" R%.2d = "REG"\n", n, fp->gpr[n], n+16, fp->gpr[n+16]); } else { for (n = 0; n < 7; ++n) - printf("R%.2ld = "REG" R%.2ld = "REG"\n", + printf("R%.2d = "REG" R%.2d = "REG"\n", n, fp->gpr[n], n+7, fp->gpr[n+7]); } #else for (n = 0; n < 32; ++n) { - printf("R%.2d = %.8x%s", n, fp->gpr[n], + printf("R%.2d = %.8lx%s", n, fp->gpr[n], (n & 3) == 3? "\n": " "); if (n == 12 && !FULL_REGS(fp)) { printf("\n"); @@ -1789,9 +1790,9 @@ static void dump_206_sprs(void) /* Actually some of these pre-date 2.06, but whatevs */ - printf("srr0 = %.16lx srr1 = %.16lx dsisr = %.8x\n", + printf("srr0 = %.16lx srr1 = %.16lx dsisr = %.8lx\n", mfspr(SPRN_SRR0), mfspr(SPRN_SRR1), mfspr(SPRN_DSISR)); - printf("dscr = %.16lx ppr = %.16lx pir = %.8x\n", + printf("dscr = %.16lx ppr = %.16lx pir = %.8lx\n", mfspr(SPRN_DSCR), mfspr(SPRN_PPR), mfspr(SPRN_PIR)); printf("amr = %.16lx uamor = %.16lx\n", mfspr(SPRN_AMR), mfspr(SPRN_UAMOR)); @@ -1799,11 +1800,11 @@ static void dump_206_sprs(void) if (!(mfmsr() & MSR_HV)) return; - printf("sdr1 = %.16lx hdar = %.16lx hdsisr = %.8x\n", + printf("sdr1 = %.16lx hdar = %.16lx hdsisr = %.8lx\n", mfspr(SPRN_SDR1), mfspr(SPRN_HDAR), mfspr(SPRN_HDSISR)); printf("hsrr0 = %.16lx hsrr1 = %.16lx hdec = %.16lx\n", mfspr(SPRN_HSRR0), mfspr(SPRN_HSRR1), mfspr(SPRN_HDEC)); - printf("lpcr = %.16lx pcr = %.16lx lpidr = %.8x\n", + printf("lpcr = %.16lx pcr = %.16lx lpidr = %.8lx\n", mfspr(SPRN_LPCR), mfspr(SPRN_PCR), mfspr(SPRN_LPID)); printf("hsprg0 = %.16lx hsprg1 = %.16lx amor = %.16lx\n", mfspr(SPRN_HSPRG0), mfspr(SPRN_HSPRG1), mfspr(SPRN_AMOR)); @@ -1820,10 +1821,10 @@ static void dump_207_sprs(void) if (!cpu_has_feature(CPU_FTR_ARCH_207S)) return; - printf("dpdes = %.16lx tir = %.16lx cir = %.8x\n", + printf("dpdes = %.16lx tir = %.16lx cir = %.8lx\n", mfspr(SPRN_DPDES), mfspr(SPRN_TIR), mfspr(SPRN_CIR)); - printf("fscr = %.16lx tar = %.16lx pspb = %.8x\n", + printf("fscr = %.16lx tar = %.16lx pspb = %.8lx\n", mfspr(SPRN_FSCR), mfspr(SPRN_TAR), mfspr(SPRN_PSPB)); msr = mfmsr(); @@ -1836,12 +1837,12 @@ static void dump_207_sprs(void) printf("mmcr0 = %.16lx mmcr1 = %.16lx mmcr2 = %.16lx\n", mfspr(SPRN_MMCR0), mfspr(SPRN_MMCR1), mfspr(SPRN_MMCR2)); - printf("pmc1 = %.8x pmc2 = %.8x pmc3 = %.8x pmc4 = %.8x\n", + printf("pmc1 = %.8lx pmc2 = %.8lx pmc3 = %.8lx pmc4 = %.8lx\n", mfspr(SPRN_PMC1), mfspr(SPRN_PMC2), mfspr(SPRN_PMC3), mfspr(SPRN_PMC4)); - printf("mmcra = %.16lx siar = %.16lx pmc5 = %.8x\n", + printf("mmcra = %.16lx siar = %.16lx pmc5 = %.8lx\n", mfspr(SPRN_MMCRA), mfspr(SPRN_SIAR), mfspr(SPRN_PMC5)); - printf("sdar = %.16lx sier = %.16lx pmc6 = %.8x\n", + printf("sdar = %.16lx sier = %.16lx pmc6 = %.8lx\n", mfspr(SPRN_SDAR), mfspr(SPRN_SIER), mfspr(SPRN_PMC6)); printf("ebbhr = %.16lx ebbrr = %.16lx bescr = %.16lx\n", mfspr(SPRN_EBBHR), mfspr(SPRN_EBBRR), mfspr(SPRN_BESCR)); @@ -2345,31 +2346,31 @@ static void dump_one_paca(int cpu) printf("paca for cpu 0x%x @ %px:\n", cpu, p); - printf(" %-*s = %s\n", 20, "possible", cpu_possible(cpu) ? "yes" : "no"); - printf(" %-*s = %s\n", 20, "present", cpu_present(cpu) ? "yes" : "no"); - printf(" %-*s = %s\n", 20, "online", cpu_online(cpu) ? "yes" : "no"); + printf(" %-*s = %s\n", 25, "possible", cpu_possible(cpu) ? "yes" : "no"); + printf(" %-*s = %s\n", 25, "present", cpu_present(cpu) ? "yes" : "no"); + printf(" %-*s = %s\n", 25, "online", cpu_online(cpu) ? "yes" : "no"); -#define DUMP(paca, name, format) \ - printf(" %-*s = %#-*"format"\t(0x%lx)\n", 20, #name, 18, paca->name, \ +#define DUMP(paca, name, format) \ + printf(" %-*s = "format"\t(0x%lx)\n", 25, #name, 18, paca->name, \ offsetof(struct paca_struct, name)); - DUMP(p, lock_token, "x"); - DUMP(p, paca_index, "x"); - DUMP(p, kernel_toc, "lx"); - DUMP(p, kernelbase, "lx"); - DUMP(p, kernel_msr, "lx"); - DUMP(p, emergency_sp, "px"); + DUMP(p, lock_token, "%#-*x"); + DUMP(p, paca_index, "%#-*x"); + DUMP(p, kernel_toc, "%#-*llx"); + DUMP(p, kernelbase, "%#-*llx"); + DUMP(p, kernel_msr, "%#-*llx"); + DUMP(p, emergency_sp, "%-*px"); #ifdef CONFIG_PPC_BOOK3S_64 - DUMP(p, nmi_emergency_sp, "px"); - DUMP(p, mc_emergency_sp, "px"); - DUMP(p, in_nmi, "x"); - DUMP(p, in_mce, "x"); - DUMP(p, hmi_event_available, "x"); + DUMP(p, nmi_emergency_sp, "%-*px"); + DUMP(p, mc_emergency_sp, "%-*px"); + DUMP(p, in_nmi, "%#-*x"); + DUMP(p, in_mce, "%#-*x"); + DUMP(p, hmi_event_available, "%#-*x"); #endif - DUMP(p, data_offset, "lx"); - DUMP(p, hw_cpu_id, "x"); - DUMP(p, cpu_start, "x"); - DUMP(p, kexec_state, "x"); + DUMP(p, data_offset, "%#-*llx"); + DUMP(p, hw_cpu_id, "%#-*x"); + DUMP(p, cpu_start, "%#-*x"); + DUMP(p, kexec_state, "%#-*x"); #ifdef CONFIG_PPC_BOOK3S_64 for (i = 0; i < SLB_NUM_BOLTED; i++) { u64 esid, vsid; @@ -2381,58 +2382,69 @@ static void dump_one_paca(int cpu) vsid = be64_to_cpu(p->slb_shadow_ptr->save_area[i].vsid); if (esid || vsid) { - printf(" slb_shadow[%d]: = 0x%016lx 0x%016lx\n", - i, esid, vsid); + printf(" %-*s[%d] = 0x%016llx 0x%016llx\n", + 22, "slb_shadow", i, esid, vsid); } } - DUMP(p, vmalloc_sllp, "x"); - DUMP(p, slb_cache_ptr, "x"); + DUMP(p, vmalloc_sllp, "%#-*x"); + DUMP(p, slb_cache_ptr, "%#-*x"); for (i = 0; i < SLB_CACHE_ENTRIES; i++) - printf(" slb_cache[%d]: = 0x%016lx\n", i, p->slb_cache[i]); + printf(" %-*s[%d] = 0x%016x\n", + 22, "slb_cache", i, p->slb_cache[i]); - DUMP(p, rfi_flush_fallback_area, "px"); + DUMP(p, rfi_flush_fallback_area, "%-*px"); #endif - DUMP(p, dscr_default, "llx"); + DUMP(p, dscr_default, "%#-*llx"); #ifdef CONFIG_PPC_BOOK3E - DUMP(p, pgd, "px"); - DUMP(p, kernel_pgd, "px"); - DUMP(p, tcd_ptr, "px"); - DUMP(p, mc_kstack, "px"); - DUMP(p, crit_kstack, "px"); - DUMP(p, dbg_kstack, "px"); + DUMP(p, pgd, "%-*px"); + DUMP(p, kernel_pgd, "%-*px"); + DUMP(p, tcd_ptr, "%-*px"); + DUMP(p, mc_kstack, "%-*px"); + DUMP(p, crit_kstack, "%-*px"); + DUMP(p, dbg_kstack, "%-*px"); #endif - DUMP(p, __current, "px"); - DUMP(p, kstack, "lx"); - printf(" kstack_base = 0x%016lx\n", p->kstack & ~(THREAD_SIZE - 1)); - DUMP(p, stab_rr, "lx"); - DUMP(p, saved_r1, "lx"); - DUMP(p, trap_save, "x"); - DUMP(p, irq_soft_mask, "x"); - DUMP(p, irq_happened, "x"); - DUMP(p, io_sync, "x"); - DUMP(p, irq_work_pending, "x"); - DUMP(p, nap_state_lost, "x"); - DUMP(p, sprg_vdso, "llx"); + DUMP(p, __current, "%-*px"); + DUMP(p, kstack, "%#-*llx"); + printf(" %-*s = 0x%016llx\n", 25, "kstack_base", p->kstack & ~(THREAD_SIZE - 1)); + DUMP(p, stab_rr, "%#-*llx"); + DUMP(p, saved_r1, "%#-*llx"); + DUMP(p, trap_save, "%#-*x"); + DUMP(p, irq_soft_mask, "%#-*x"); + DUMP(p, irq_happened, "%#-*x"); + DUMP(p, io_sync, "%#-*x"); + DUMP(p, irq_work_pending, "%#-*x"); + DUMP(p, nap_state_lost, "%#-*x"); + DUMP(p, sprg_vdso, "%#-*llx"); #ifdef CONFIG_PPC_TRANSACTIONAL_MEM - DUMP(p, tm_scratch, "llx"); + DUMP(p, tm_scratch, "%#-*llx"); #endif #ifdef CONFIG_PPC_POWERNV - DUMP(p, core_idle_state_ptr, "px"); - DUMP(p, thread_idle_state, "x"); - DUMP(p, thread_mask, "x"); - DUMP(p, subcore_sibling_mask, "x"); + DUMP(p, core_idle_state_ptr, "%-*px"); + DUMP(p, thread_idle_state, "%#-*x"); + DUMP(p, thread_mask, "%#-*x"); + DUMP(p, subcore_sibling_mask, "%#-*x"); + DUMP(p, thread_sibling_pacas, "%-*px"); + DUMP(p, requested_psscr, "%#-*llx"); + DUMP(p, stop_sprs.pid, "%#-*llx"); + DUMP(p, stop_sprs.ldbar, "%#-*llx"); + DUMP(p, stop_sprs.fscr, "%#-*llx"); + DUMP(p, stop_sprs.hfscr, "%#-*llx"); + DUMP(p, stop_sprs.mmcr1, "%#-*llx"); + DUMP(p, stop_sprs.mmcr2, "%#-*llx"); + DUMP(p, stop_sprs.mmcra, "%#-*llx"); + DUMP(p, dont_stop.counter, "%#-*x"); #endif - DUMP(p, accounting.utime, "llx"); - DUMP(p, accounting.stime, "llx"); - DUMP(p, accounting.utime_scaled, "llx"); - DUMP(p, accounting.starttime, "llx"); - DUMP(p, accounting.starttime_user, "llx"); - DUMP(p, accounting.startspurr, "llx"); - DUMP(p, accounting.utime_sspurr, "llx"); - DUMP(p, accounting.steal_time, "llx"); + DUMP(p, accounting.utime, "%#-*lx"); + DUMP(p, accounting.stime, "%#-*lx"); + DUMP(p, accounting.utime_scaled, "%#-*lx"); + DUMP(p, accounting.starttime, "%#-*lx"); + DUMP(p, accounting.starttime_user, "%#-*lx"); + DUMP(p, accounting.startspurr, "%#-*lx"); + DUMP(p, accounting.utime_sspurr, "%#-*lx"); + DUMP(p, accounting.steal_time, "%#-*lx"); #undef DUMP catch_memory_errors = 0; @@ -2578,7 +2590,7 @@ static void dump_by_size(unsigned long addr, long count, int size) default: val = 0; } - printf("%0*lx", size * 2, val); + printf("%0*llx", size * 2, val); } printf("\n"); } @@ -2742,7 +2754,7 @@ generic_inst_dump(unsigned long adr, long count, int praddr, dotted = 0; last_inst = inst; if (praddr) - printf(REG" %.8x", adr, inst); + printf(REG" %.8lx", adr, inst); printf("\t"); dump_func(inst, adr); printf("\n"); @@ -2874,7 +2886,7 @@ memdiffs(unsigned char *p1, unsigned char *p2, unsigned nb, unsigned maxpr) for( n = nb; n > 0; --n ) if( *p1++ != *p2++ ) if( ++prt <= maxpr ) - printf("%.16x %.2x # %.16x %.2x\n", p1 - 1, + printf("%px %.2x # %px %.2x\n", p1 - 1, p1[-1], p2 - 1, p2[-1]); if( prt > maxpr ) printf("Total of %d differences\n", prt); @@ -2934,13 +2946,13 @@ memzcan(void) if (ok && !ook) { printf("%.8x .. ", a); } else if (!ok && ook) - printf("%.8x\n", a - mskip); + printf("%.8lx\n", a - mskip); ook = ok; if (a + mskip < a) break; } if (ook) - printf("%.8x\n", a - mskip); + printf("%.8lx\n", a - mskip); } static void show_task(struct task_struct *tsk) @@ -3024,13 +3036,13 @@ static void show_pte(unsigned long addr) return; } - printf("pgd @ 0x%016lx\n", pgdir); + printf("pgd @ 0x%px\n", pgdir); if (pgd_huge(*pgdp)) { format_pte(pgdp, pgd_val(*pgdp)); return; } - printf("pgdp @ 0x%016lx = 0x%016lx\n", pgdp, pgd_val(*pgdp)); + printf("pgdp @ 0x%px = 0x%016lx\n", pgdp, pgd_val(*pgdp)); pudp = pud_offset(pgdp, addr); @@ -3044,7 +3056,7 @@ static void show_pte(unsigned long addr) return; } - printf("pudp @ 0x%016lx = 0x%016lx\n", pudp, pud_val(*pudp)); + printf("pudp @ 0x%px = 0x%016lx\n", pudp, pud_val(*pudp)); pmdp = pmd_offset(pudp, addr); @@ -3057,7 +3069,7 @@ static void show_pte(unsigned long addr) format_pte(pmdp, pmd_val(*pmdp)); return; } - printf("pmdp @ 0x%016lx = 0x%016lx\n", pmdp, pmd_val(*pmdp)); + printf("pmdp @ 0x%px = 0x%016lx\n", pmdp, pmd_val(*pmdp)); ptep = pte_offset_map(pmdp, addr); if (pte_none(*ptep)) { @@ -3456,9 +3468,9 @@ static void dump_tlb_44x(void) asm volatile("tlbre %0,%1,0" : "=r" (w0) : "r" (i)); asm volatile("tlbre %0,%1,1" : "=r" (w1) : "r" (i)); asm volatile("tlbre %0,%1,2" : "=r" (w2) : "r" (i)); - printf("[%02x] %08x %08x %08x ", i, w0, w1, w2); + printf("[%02x] %08lx %08lx %08lx ", i, w0, w1, w2); if (w0 & PPC44x_TLB_VALID) { - printf("V %08x -> %01x%08x %c%c%c%c%c", + printf("V %08lx -> %01lx%08lx %c%c%c%c%c", w0 & PPC44x_TLB_EPN_MASK, w1 & PPC44x_TLB_ERPN_MASK, w1 & PPC44x_TLB_RPN_MASK, @@ -3882,19 +3894,19 @@ static void dump_spu_fields(struct spu *spu) DUMP_FIELD(spu, "0x%lx", ls_size); DUMP_FIELD(spu, "0x%x", node); DUMP_FIELD(spu, "0x%lx", flags); - DUMP_FIELD(spu, "%d", class_0_pending); - DUMP_FIELD(spu, "0x%lx", class_0_dar); - DUMP_FIELD(spu, "0x%lx", class_1_dar); - DUMP_FIELD(spu, "0x%lx", class_1_dsisr); - DUMP_FIELD(spu, "0x%lx", irqs[0]); - DUMP_FIELD(spu, "0x%lx", irqs[1]); - DUMP_FIELD(spu, "0x%lx", irqs[2]); + DUMP_FIELD(spu, "%llu", class_0_pending); + DUMP_FIELD(spu, "0x%llx", class_0_dar); + DUMP_FIELD(spu, "0x%llx", class_1_dar); + DUMP_FIELD(spu, "0x%llx", class_1_dsisr); + DUMP_FIELD(spu, "0x%x", irqs[0]); + DUMP_FIELD(spu, "0x%x", irqs[1]); + DUMP_FIELD(spu, "0x%x", irqs[2]); DUMP_FIELD(spu, "0x%x", slb_replace); DUMP_FIELD(spu, "%d", pid); DUMP_FIELD(spu, "0x%p", mm); DUMP_FIELD(spu, "0x%p", ctx); DUMP_FIELD(spu, "0x%p", rq); - DUMP_FIELD(spu, "0x%p", timestamp); + DUMP_FIELD(spu, "0x%llx", timestamp); DUMP_FIELD(spu, "0x%lx", problem_phys); DUMP_FIELD(spu, "0x%p", problem); DUMP_VALUE("0x%x", problem->spu_runcntl_RW, @@ -3925,7 +3937,7 @@ static void dump_spu_ls(unsigned long num, int subcmd) __delay(200); } else { catch_memory_errors = 0; - printf("*** Error: accessing spu info for spu %d\n", num); + printf("*** Error: accessing spu info for spu %ld\n", num); return; } catch_memory_errors = 0; diff --git a/drivers/hwmon/ibmpowernv.c b/drivers/hwmon/ibmpowernv.c index 5ccdd0b52650..0298745d46e4 100644 --- a/drivers/hwmon/ibmpowernv.c +++ b/drivers/hwmon/ibmpowernv.c @@ -51,6 +51,7 @@ enum sensors { POWER_SUPPLY, POWER_INPUT, CURRENT, + ENERGY, MAX_SENSOR_TYPE, }; @@ -78,6 +79,7 @@ static struct sensor_group { { "in" }, { "power" }, { "curr" }, + { "energy" }, }; struct sensor_data { @@ -101,9 +103,10 @@ static ssize_t show_sensor(struct device *dev, struct device_attribute *devattr, struct sensor_data *sdata = container_of(devattr, struct sensor_data, dev_attr); ssize_t ret; - u32 x; + u64 x; + + ret = opal_get_sensor_data_u64(sdata->id, &x); - ret = opal_get_sensor_data(sdata->id, &x); if (ret) return ret; @@ -114,7 +117,7 @@ static ssize_t show_sensor(struct device *dev, struct device_attribute *devattr, else if (sdata->type == POWER_INPUT) x *= 1000000; - return sprintf(buf, "%u\n", x); + return sprintf(buf, "%llu\n", x); } static ssize_t show_label(struct device *dev, struct device_attribute *devattr, diff --git a/drivers/macintosh/via-pmu.c b/drivers/macintosh/via-pmu.c index 433dbeddfcf9..a3b6a4a703ab 100644 --- a/drivers/macintosh/via-pmu.c +++ b/drivers/macintosh/via-pmu.c @@ -274,7 +274,7 @@ int __init find_via_pmu(void) u64 taddr; const u32 *reg; - if (via != 0) + if (via) return 1; vias = of_find_node_by_name(NULL, "via-pmu"); if (vias == NULL) @@ -1152,7 +1152,7 @@ pmu_queue_request(struct adb_request *req) req->complete = 0; spin_lock_irqsave(&pmu_lock, flags); - if (current_req != 0) { + if (current_req) { last_req->next = req; last_req = req; } else { @@ -1227,7 +1227,7 @@ pmu_start(void) /* assert pmu_state == idle */ /* get the packet to send */ req = current_req; - if (req == 0 || pmu_state != idle + if (!req || pmu_state != idle || (/*req->reply_expected && */req_awaiting_reply)) return; @@ -1382,7 +1382,7 @@ next: if ((1 << pirq) & PMU_INT_ADB) { if ((data[0] & PMU_INT_ADB_AUTO) == 0) { struct adb_request *req = req_awaiting_reply; - if (req == 0) { + if (!req) { printk(KERN_ERR "PMU: extra ADB reply\n"); return; } @@ -1749,7 +1749,7 @@ pmu_shutdown(void) int pmu_present(void) { - return via != 0; + return via != NULL; } #if defined(CONFIG_SUSPEND) && defined(CONFIG_PPC32) @@ -2081,7 +2081,7 @@ pmu_open(struct inode *inode, struct file *file) unsigned long flags; pp = kmalloc(sizeof(struct pmu_private), GFP_KERNEL); - if (pp == 0) + if (!pp) return -ENOMEM; pp->rb_get = pp->rb_put = 0; spin_lock_init(&pp->lock); @@ -2107,7 +2107,7 @@ pmu_read(struct file *file, char __user *buf, unsigned long flags; int ret = 0; - if (count < 1 || pp == 0) + if (count < 1 || !pp) return -EINVAL; if (!access_ok(VERIFY_WRITE, buf, count)) return -EFAULT; @@ -2164,7 +2164,7 @@ pmu_fpoll(struct file *filp, poll_table *wait) __poll_t mask = 0; unsigned long flags; - if (pp == 0) + if (!pp) return 0; poll_wait(filp, &pp->wait, wait); spin_lock_irqsave(&pp->lock, flags); @@ -2180,7 +2180,7 @@ pmu_release(struct inode *inode, struct file *file) struct pmu_private *pp = file->private_data; unsigned long flags; - if (pp != 0) { + if (pp) { file->private_data = NULL; spin_lock_irqsave(&all_pvt_lock, flags); list_del(&pp->list); diff --git a/drivers/macintosh/windfarm_pm121.c b/drivers/macintosh/windfarm_pm121.c index 4d72d8f58cb6..97634e030991 100644 --- a/drivers/macintosh/windfarm_pm121.c +++ b/drivers/macintosh/windfarm_pm121.c @@ -710,7 +710,7 @@ static void pm121_create_cpu_fans(void) wf_cpu_pid_init(&pm121_cpu_state->pid, &pid_param); pr_debug("pm121: CPU Fan control initialized.\n"); - pr_debug(" ttarged=%d.%03d, tmax=%d.%03d, min=%d RPM, max=%d RPM,\n", + pr_debug(" ttarget=%d.%03d, tmax=%d.%03d, min=%d RPM, max=%d RPM,\n", FIX32TOPRINT(pid_param.ttarget), FIX32TOPRINT(pid_param.tmax), pid_param.min, pid_param.max); diff --git a/drivers/macintosh/windfarm_pm81.c b/drivers/macintosh/windfarm_pm81.c index d9ea45581b9e..346c91744442 100644 --- a/drivers/macintosh/windfarm_pm81.c +++ b/drivers/macintosh/windfarm_pm81.c @@ -455,7 +455,7 @@ static void wf_smu_create_cpu_fans(void) wf_cpu_pid_init(&wf_smu_cpu_fans->pid, &pid_param); DBG("wf: CPU Fan control initialized.\n"); - DBG(" ttarged=%d.%03d, tmax=%d.%03d, min=%d RPM, max=%d RPM\n", + DBG(" ttarget=%d.%03d, tmax=%d.%03d, min=%d RPM, max=%d RPM\n", FIX32TOPRINT(pid_param.ttarget), FIX32TOPRINT(pid_param.tmax), pid_param.min, pid_param.max); diff --git a/drivers/macintosh/windfarm_pm91.c b/drivers/macintosh/windfarm_pm91.c index 7fd73dcb2b0a..a8a47c62a74b 100644 --- a/drivers/macintosh/windfarm_pm91.c +++ b/drivers/macintosh/windfarm_pm91.c @@ -200,7 +200,7 @@ static void wf_smu_create_cpu_fans(void) wf_cpu_pid_init(&wf_smu_cpu_fans->pid, &pid_param); DBG("wf: CPU Fan control initialized.\n"); - DBG(" ttarged=%d.%03d, tmax=%d.%03d, min=%d RPM, max=%d RPM\n", + DBG(" ttarget=%d.%03d, tmax=%d.%03d, min=%d RPM, max=%d RPM\n", FIX32TOPRINT(pid_param.ttarget), FIX32TOPRINT(pid_param.tmax), pid_param.min, pid_param.max); diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c index 83f1d08058fc..2e8b187956bc 100644 --- a/drivers/misc/cxl/pci.c +++ b/drivers/misc/cxl/pci.c @@ -514,9 +514,9 @@ static int init_implementation_adapter_regs_psl9(struct cxl *adapter, cxl_p1_write(adapter, CXL_PSL9_FIR_CNTL, psl_fircntl); /* Setup the PSL to transmit packets on the PCIe before the - * CAPP is enabled + * CAPP is enabled. Make sure that CAPP virtual machines are disabled */ - cxl_p1_write(adapter, CXL_PSL9_DSNDCTL, 0x0001001000002A10ULL); + cxl_p1_write(adapter, CXL_PSL9_DSNDCTL, 0x0001001000012A10ULL); /* * A response to an ASB_Notify request is returned by the diff --git a/drivers/misc/cxl/sysfs.c b/drivers/misc/cxl/sysfs.c index 95285b7f636f..90aa4eee8ccd 100644 --- a/drivers/misc/cxl/sysfs.c +++ b/drivers/misc/cxl/sysfs.c @@ -343,12 +343,20 @@ static ssize_t prefault_mode_store(struct device *device, struct cxl_afu *afu = to_cxl_afu(device); enum prefault_modes mode = -1; - if (!strncmp(buf, "work_element_descriptor", 23)) - mode = CXL_PREFAULT_WED; - if (!strncmp(buf, "all", 3)) - mode = CXL_PREFAULT_ALL; if (!strncmp(buf, "none", 4)) mode = CXL_PREFAULT_NONE; + else { + if (!radix_enabled()) { + + /* only allowed when not in radix mode */ + if (!strncmp(buf, "work_element_descriptor", 23)) + mode = CXL_PREFAULT_WED; + if (!strncmp(buf, "all", 3)) + mode = CXL_PREFAULT_ALL; + } else { + dev_err(device, "Cannot prefault with radix enabled\n"); + } + } if (mode == -1) return -EINVAL; diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 9791364925dc..3751a511e2b8 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -365,7 +365,7 @@ COND_SYSCALL(s390_pci_mmio_write); COND_SYSCALL_COMPAT(s390_ipc); /* powerpc */ -cond_syscall(ppc_rtas); +COND_SYSCALL(rtas); COND_SYSCALL(spu_run); COND_SYSCALL(spu_create); COND_SYSCALL(subpage_prot); diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index c4f0f2e4126e..dd6c0a2ad969 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -110,11 +110,7 @@ config GENERIC_TRACER # config TRACING_SUPPORT bool - # PPC32 has no irqflags tracing support, but it can use most of the - # tracers anyway, they were tested to build and work. Note that new - # exceptions to this list aren't welcomed, better implement the - # irqflags tracing for your architecture. - depends on TRACE_IRQFLAGS_SUPPORT || PPC32 + depends on TRACE_IRQFLAGS_SUPPORT depends on STACKTRACE_SUPPORT default y diff --git a/tools/testing/selftests/powerpc/Makefile b/tools/testing/selftests/powerpc/Makefile index f6b1338730db..201b598558b9 100644 --- a/tools/testing/selftests/powerpc/Makefile +++ b/tools/testing/selftests/powerpc/Makefile @@ -17,7 +17,6 @@ SUB_DIRS = alignment \ benchmarks \ cache_shape \ copyloops \ - context_switch \ dscr \ mm \ pmu \ diff --git a/tools/testing/selftests/powerpc/alignment/.gitignore b/tools/testing/selftests/powerpc/alignment/.gitignore index 1d980e3d7039..9d383073b7ad 100644 --- a/tools/testing/selftests/powerpc/alignment/.gitignore +++ b/tools/testing/selftests/powerpc/alignment/.gitignore @@ -3,3 +3,4 @@ copy_first_unaligned paste_unaligned paste_last_unaligned copy_paste_unaligned_common +alignment_handler diff --git a/tools/testing/selftests/powerpc/benchmarks/exec_target.c b/tools/testing/selftests/powerpc/benchmarks/exec_target.c index 3c9c144192be..c14b0fc1edde 100644 --- a/tools/testing/selftests/powerpc/benchmarks/exec_target.c +++ b/tools/testing/selftests/powerpc/benchmarks/exec_target.c @@ -6,8 +6,11 @@ * Copyright 2018, Anton Blanchard, IBM Corp. */ -void _exit(int); +#define _GNU_SOURCE +#include <unistd.h> +#include <sys/syscall.h> + void _start(void) { - _exit(0); + syscall(SYS_exit, 0); } diff --git a/tools/testing/selftests/powerpc/context_switch/.gitignore b/tools/testing/selftests/powerpc/context_switch/.gitignore deleted file mode 100644 index c1431af7b51c..000000000000 --- a/tools/testing/selftests/powerpc/context_switch/.gitignore +++ /dev/null @@ -1 +0,0 @@ -cp_abort diff --git a/tools/testing/selftests/powerpc/context_switch/Makefile b/tools/testing/selftests/powerpc/context_switch/Makefile deleted file mode 100644 index e9351bb4285d..000000000000 --- a/tools/testing/selftests/powerpc/context_switch/Makefile +++ /dev/null @@ -1,5 +0,0 @@ -TEST_GEN_PROGS := cp_abort - -include ../../lib.mk - -$(TEST_GEN_PROGS): ../harness.c ../utils.c diff --git a/tools/testing/selftests/powerpc/context_switch/cp_abort.c b/tools/testing/selftests/powerpc/context_switch/cp_abort.c deleted file mode 100644 index 5a5b55afda0e..000000000000 --- a/tools/testing/selftests/powerpc/context_switch/cp_abort.c +++ /dev/null @@ -1,110 +0,0 @@ -/* - * Adapted from Anton Blanchard's context switch microbenchmark. - * - * Copyright 2009, Anton Blanchard, IBM Corporation. - * Copyright 2016, Mikey Neuling, Chris Smart, IBM Corporation. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * - * This program tests the copy paste abort functionality of a P9 - * (or later) by setting up two processes on the same CPU, one - * which executes the copy instruction and the other which - * executes paste. - * - * The paste instruction should never succeed, as the cp_abort - * instruction is called by the kernel during a context switch. - * - */ - -#define _GNU_SOURCE - -#include <stdio.h> -#include <unistd.h> -#include <stdlib.h> -#include "utils.h" -#include <sched.h> - -#define READ_FD 0 -#define WRITE_FD 1 - -#define NUM_LOOPS 1000 - -/* This defines the "paste" instruction from Power ISA 3.0 Book II, section 4.4. */ -#define PASTE(RA, RB, L, RC) \ - .long (0x7c00070c | (RA) << (31-15) | (RB) << (31-20) | (L) << (31-10) | (RC) << (31-31)) - -int paste(void *i) -{ - int cr; - - asm volatile(str(PASTE(0, %1, 1, 1))";" - "mfcr %0;" - : "=r" (cr) - : "b" (i) - : "memory" - ); - return cr; -} - -/* This defines the "copy" instruction from Power ISA 3.0 Book II, section 4.4. */ -#define COPY(RA, RB, L) \ - .long (0x7c00060c | (RA) << (31-15) | (RB) << (31-20) | (L) << (31-10)) - -void copy(void *i) -{ - asm volatile(str(COPY(0, %0, 1))";" - : - : "b" (i) - : "memory" - ); -} - -int test_cp_abort(void) -{ - /* 128 bytes for a full cache line */ - char buf[128] __cacheline_aligned; - cpu_set_t cpuset; - int fd1[2], fd2[2], pid; - char c; - - /* only run this test on a P9 or later */ - SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_3_00)); - - /* - * Run both processes on the same CPU, so that copy is more likely - * to leak into a paste. - */ - CPU_ZERO(&cpuset); - CPU_SET(pick_online_cpu(), &cpuset); - FAIL_IF(sched_setaffinity(0, sizeof(cpuset), &cpuset)); - - FAIL_IF(pipe(fd1) || pipe(fd2)); - - pid = fork(); - FAIL_IF(pid < 0); - - if (!pid) { - for (int i = 0; i < NUM_LOOPS; i++) { - FAIL_IF((write(fd1[WRITE_FD], &c, 1)) != 1); - FAIL_IF((read(fd2[READ_FD], &c, 1)) != 1); - /* A paste succeeds if CR0 EQ bit is set */ - FAIL_IF(paste(buf) & 0x20000000); - } - } else { - for (int i = 0; i < NUM_LOOPS; i++) { - FAIL_IF((read(fd1[READ_FD], &c, 1)) != 1); - copy(buf); - FAIL_IF((write(fd2[WRITE_FD], &c, 1) != 1)); - } - } - return 0; - -} - -int main(int argc, char *argv[]) -{ - return test_harness(test_cp_abort, "cp_abort"); -} diff --git a/tools/testing/selftests/powerpc/include/reg.h b/tools/testing/selftests/powerpc/include/reg.h index 4afdebcce4cd..7f348c059bc2 100644 --- a/tools/testing/selftests/powerpc/include/reg.h +++ b/tools/testing/selftests/powerpc/include/reg.h @@ -54,6 +54,7 @@ #define SPRN_DSCR_PRIV 0x11 /* Privilege State DSCR */ #define SPRN_DSCR 0x03 /* Data Stream Control Register */ #define SPRN_PPR 896 /* Program Priority Register */ +#define SPRN_AMR 13 /* Authority Mask Register - problem state */ /* TEXASR register bits */ #define TEXASR_FC 0xFE00000000000000 diff --git a/tools/testing/selftests/powerpc/ptrace/.gitignore b/tools/testing/selftests/powerpc/ptrace/.gitignore index 349acfafc95b..9dcc16ea8179 100644 --- a/tools/testing/selftests/powerpc/ptrace/.gitignore +++ b/tools/testing/selftests/powerpc/ptrace/.gitignore @@ -8,3 +8,4 @@ ptrace-vsx ptrace-tm-vsx ptrace-tm-spd-vsx ptrace-tm-spr +ptrace-hwbreak diff --git a/tools/testing/selftests/powerpc/ptrace/Makefile b/tools/testing/selftests/powerpc/ptrace/Makefile index 480305266504..4f5957538908 100644 --- a/tools/testing/selftests/powerpc/ptrace/Makefile +++ b/tools/testing/selftests/powerpc/ptrace/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 TEST_PROGS := ptrace-gpr ptrace-tm-gpr ptrace-tm-spd-gpr \ ptrace-tar ptrace-tm-tar ptrace-tm-spd-tar ptrace-vsx ptrace-tm-vsx \ - ptrace-tm-spd-vsx ptrace-tm-spr + ptrace-tm-spd-vsx ptrace-tm-spr ptrace-hwbreak ptrace-pkey core-pkey include ../../lib.mk @@ -9,6 +9,9 @@ all: $(TEST_PROGS) CFLAGS += -m64 -I../../../../../usr/include -I../tm -mhtm -fno-pie +ptrace-pkey core-pkey: child.h +ptrace-pkey core-pkey: LDLIBS += -pthread + $(TEST_PROGS): ../harness.c ../utils.c ../lib/reg.S ptrace.h clean: diff --git a/tools/testing/selftests/powerpc/ptrace/child.h b/tools/testing/selftests/powerpc/ptrace/child.h new file mode 100644 index 000000000000..d7275b7b33dc --- /dev/null +++ b/tools/testing/selftests/powerpc/ptrace/child.h @@ -0,0 +1,139 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Helper functions to sync execution between parent and child processes. + * + * Copyright 2018, Thiago Jung Bauermann, IBM Corporation. + */ +#include <stdio.h> +#include <stdbool.h> +#include <semaphore.h> + +/* + * Information in a shared memory location for synchronization between child and + * parent. + */ +struct child_sync { + /* The parent waits on this semaphore. */ + sem_t sem_parent; + + /* If true, the child should give up as well. */ + bool parent_gave_up; + + /* The child waits on this semaphore. */ + sem_t sem_child; + + /* If true, the parent should give up as well. */ + bool child_gave_up; +}; + +#define CHILD_FAIL_IF(x, sync) \ + do { \ + if (x) { \ + fprintf(stderr, \ + "[FAIL] Test FAILED on line %d\n", __LINE__); \ + (sync)->child_gave_up = true; \ + prod_parent(sync); \ + return 1; \ + } \ + } while (0) + +#define PARENT_FAIL_IF(x, sync) \ + do { \ + if (x) { \ + fprintf(stderr, \ + "[FAIL] Test FAILED on line %d\n", __LINE__); \ + (sync)->parent_gave_up = true; \ + prod_child(sync); \ + return 1; \ + } \ + } while (0) + +#define PARENT_SKIP_IF_UNSUPPORTED(x, sync) \ + do { \ + if ((x) == -1 && (errno == ENODEV || errno == EINVAL)) { \ + (sync)->parent_gave_up = true; \ + prod_child(sync); \ + SKIP_IF(1); \ + } \ + } while (0) + +int init_child_sync(struct child_sync *sync) +{ + int ret; + + ret = sem_init(&sync->sem_parent, 1, 0); + if (ret) { + perror("Semaphore initialization failed"); + return 1; + } + + ret = sem_init(&sync->sem_child, 1, 0); + if (ret) { + perror("Semaphore initialization failed"); + return 1; + } + + return 0; +} + +void destroy_child_sync(struct child_sync *sync) +{ + sem_destroy(&sync->sem_parent); + sem_destroy(&sync->sem_child); +} + +int wait_child(struct child_sync *sync) +{ + int ret; + + /* Wait until the child prods us. */ + ret = sem_wait(&sync->sem_parent); + if (ret) { + perror("Error waiting for child"); + return 1; + } + + return sync->child_gave_up; +} + +int prod_child(struct child_sync *sync) +{ + int ret; + + /* Unblock the child now. */ + ret = sem_post(&sync->sem_child); + if (ret) { + perror("Error prodding child"); + return 1; + } + + return 0; +} + +int wait_parent(struct child_sync *sync) +{ + int ret; + + /* Wait until the parent prods us. */ + ret = sem_wait(&sync->sem_child); + if (ret) { + perror("Error waiting for parent"); + return 1; + } + + return sync->parent_gave_up; +} + +int prod_parent(struct child_sync *sync) +{ + int ret; + + /* Unblock the parent now. */ + ret = sem_post(&sync->sem_parent); + if (ret) { + perror("Error prodding parent"); + return 1; + } + + return 0; +} diff --git a/tools/testing/selftests/powerpc/ptrace/core-pkey.c b/tools/testing/selftests/powerpc/ptrace/core-pkey.c new file mode 100644 index 000000000000..36bc312b1f5c --- /dev/null +++ b/tools/testing/selftests/powerpc/ptrace/core-pkey.c @@ -0,0 +1,461 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Ptrace test for Memory Protection Key registers + * + * Copyright (C) 2015 Anshuman Khandual, IBM Corporation. + * Copyright (C) 2018 IBM Corporation. + */ +#include <limits.h> +#include <linux/kernel.h> +#include <sys/mman.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <sys/time.h> +#include <sys/resource.h> +#include <fcntl.h> +#include <unistd.h> +#include "ptrace.h" +#include "child.h" + +#ifndef __NR_pkey_alloc +#define __NR_pkey_alloc 384 +#endif + +#ifndef __NR_pkey_free +#define __NR_pkey_free 385 +#endif + +#ifndef NT_PPC_PKEY +#define NT_PPC_PKEY 0x110 +#endif + +#ifndef PKEY_DISABLE_EXECUTE +#define PKEY_DISABLE_EXECUTE 0x4 +#endif + +#define AMR_BITS_PER_PKEY 2 +#define PKEY_REG_BITS (sizeof(u64) * 8) +#define pkeyshift(pkey) (PKEY_REG_BITS - ((pkey + 1) * AMR_BITS_PER_PKEY)) + +#define CORE_FILE_LIMIT (5 * 1024 * 1024) /* 5 MB should be enough */ + +static const char core_pattern_file[] = "/proc/sys/kernel/core_pattern"; + +static const char user_write[] = "[User Write (Running)]"; +static const char core_read_running[] = "[Core Read (Running)]"; + +/* Information shared between the parent and the child. */ +struct shared_info { + struct child_sync child_sync; + + /* AMR value the parent expects to read in the core file. */ + unsigned long amr; + + /* IAMR value the parent expects to read in the core file. */ + unsigned long iamr; + + /* UAMOR value the parent expects to read in the core file. */ + unsigned long uamor; + + /* When the child crashed. */ + time_t core_time; +}; + +static int sys_pkey_alloc(unsigned long flags, unsigned long init_access_rights) +{ + return syscall(__NR_pkey_alloc, flags, init_access_rights); +} + +static int sys_pkey_free(int pkey) +{ + return syscall(__NR_pkey_free, pkey); +} + +static int increase_core_file_limit(void) +{ + struct rlimit rlim; + int ret; + + ret = getrlimit(RLIMIT_CORE, &rlim); + FAIL_IF(ret); + + if (rlim.rlim_cur != RLIM_INFINITY && rlim.rlim_cur < CORE_FILE_LIMIT) { + rlim.rlim_cur = CORE_FILE_LIMIT; + + if (rlim.rlim_max != RLIM_INFINITY && + rlim.rlim_max < CORE_FILE_LIMIT) + rlim.rlim_max = CORE_FILE_LIMIT; + + ret = setrlimit(RLIMIT_CORE, &rlim); + FAIL_IF(ret); + } + + ret = getrlimit(RLIMIT_FSIZE, &rlim); + FAIL_IF(ret); + + if (rlim.rlim_cur != RLIM_INFINITY && rlim.rlim_cur < CORE_FILE_LIMIT) { + rlim.rlim_cur = CORE_FILE_LIMIT; + + if (rlim.rlim_max != RLIM_INFINITY && + rlim.rlim_max < CORE_FILE_LIMIT) + rlim.rlim_max = CORE_FILE_LIMIT; + + ret = setrlimit(RLIMIT_FSIZE, &rlim); + FAIL_IF(ret); + } + + return TEST_PASS; +} + +static int child(struct shared_info *info) +{ + bool disable_execute = true; + int pkey1, pkey2, pkey3; + int *ptr, ret; + + /* Wait until parent fills out the initial register values. */ + ret = wait_parent(&info->child_sync); + if (ret) + return ret; + + ret = increase_core_file_limit(); + FAIL_IF(ret); + + /* Get some pkeys so that we can change their bits in the AMR. */ + pkey1 = sys_pkey_alloc(0, PKEY_DISABLE_EXECUTE); + if (pkey1 < 0) { + pkey1 = sys_pkey_alloc(0, 0); + FAIL_IF(pkey1 < 0); + + disable_execute = false; + } + + pkey2 = sys_pkey_alloc(0, 0); + FAIL_IF(pkey2 < 0); + + pkey3 = sys_pkey_alloc(0, 0); + FAIL_IF(pkey3 < 0); + + info->amr |= 3ul << pkeyshift(pkey1) | 2ul << pkeyshift(pkey2); + + if (disable_execute) + info->iamr |= 1ul << pkeyshift(pkey1); + + info->uamor |= 3ul << pkeyshift(pkey1) | 3ul << pkeyshift(pkey2); + + printf("%-30s AMR: %016lx pkey1: %d pkey2: %d pkey3: %d\n", + user_write, info->amr, pkey1, pkey2, pkey3); + + mtspr(SPRN_AMR, info->amr); + + /* + * We won't use pkey3. This tests whether the kernel restores the UAMOR + * permissions after a key is freed. + */ + sys_pkey_free(pkey3); + + info->core_time = time(NULL); + + /* Crash. */ + ptr = 0; + *ptr = 1; + + /* Shouldn't get here. */ + FAIL_IF(true); + + return TEST_FAIL; +} + +/* Return file size if filename exists and pass sanity check, or zero if not. */ +static off_t try_core_file(const char *filename, struct shared_info *info, + pid_t pid) +{ + struct stat buf; + int ret; + + ret = stat(filename, &buf); + if (ret == -1) + return TEST_FAIL; + + /* Make sure we're not using a stale core file. */ + return buf.st_mtime >= info->core_time ? buf.st_size : TEST_FAIL; +} + +static Elf64_Nhdr *next_note(Elf64_Nhdr *nhdr) +{ + return (void *) nhdr + sizeof(*nhdr) + + __ALIGN_KERNEL(nhdr->n_namesz, 4) + + __ALIGN_KERNEL(nhdr->n_descsz, 4); +} + +static int check_core_file(struct shared_info *info, Elf64_Ehdr *ehdr, + off_t core_size) +{ + unsigned long *regs; + Elf64_Phdr *phdr; + Elf64_Nhdr *nhdr; + size_t phdr_size; + void *p = ehdr, *note; + int ret; + + ret = memcmp(ehdr->e_ident, ELFMAG, SELFMAG); + FAIL_IF(ret); + + FAIL_IF(ehdr->e_type != ET_CORE); + FAIL_IF(ehdr->e_machine != EM_PPC64); + FAIL_IF(ehdr->e_phoff == 0 || ehdr->e_phnum == 0); + + /* + * e_phnum is at most 65535 so calculating the size of the + * program header cannot overflow. + */ + phdr_size = sizeof(*phdr) * ehdr->e_phnum; + + /* Sanity check the program header table location. */ + FAIL_IF(ehdr->e_phoff + phdr_size < ehdr->e_phoff); + FAIL_IF(ehdr->e_phoff + phdr_size > core_size); + + /* Find the PT_NOTE segment. */ + for (phdr = p + ehdr->e_phoff; + (void *) phdr < p + ehdr->e_phoff + phdr_size; + phdr += ehdr->e_phentsize) + if (phdr->p_type == PT_NOTE) + break; + + FAIL_IF((void *) phdr >= p + ehdr->e_phoff + phdr_size); + + /* Find the NT_PPC_PKEY note. */ + for (nhdr = p + phdr->p_offset; + (void *) nhdr < p + phdr->p_offset + phdr->p_filesz; + nhdr = next_note(nhdr)) + if (nhdr->n_type == NT_PPC_PKEY) + break; + + FAIL_IF((void *) nhdr >= p + phdr->p_offset + phdr->p_filesz); + FAIL_IF(nhdr->n_descsz == 0); + + p = nhdr; + note = p + sizeof(*nhdr) + __ALIGN_KERNEL(nhdr->n_namesz, 4); + + regs = (unsigned long *) note; + + printf("%-30s AMR: %016lx IAMR: %016lx UAMOR: %016lx\n", + core_read_running, regs[0], regs[1], regs[2]); + + FAIL_IF(regs[0] != info->amr); + FAIL_IF(regs[1] != info->iamr); + FAIL_IF(regs[2] != info->uamor); + + return TEST_PASS; +} + +static int parent(struct shared_info *info, pid_t pid) +{ + char *filenames, *filename[3]; + int fd, i, ret, status; + unsigned long regs[3]; + off_t core_size; + void *core; + + /* + * Get the initial values for AMR, IAMR and UAMOR and communicate them + * to the child. + */ + ret = ptrace_read_regs(pid, NT_PPC_PKEY, regs, 3); + PARENT_SKIP_IF_UNSUPPORTED(ret, &info->child_sync); + PARENT_FAIL_IF(ret, &info->child_sync); + + info->amr = regs[0]; + info->iamr = regs[1]; + info->uamor = regs[2]; + + /* Wake up child so that it can set itself up. */ + ret = prod_child(&info->child_sync); + PARENT_FAIL_IF(ret, &info->child_sync); + + ret = wait(&status); + if (ret != pid) { + printf("Child's exit status not captured\n"); + return TEST_FAIL; + } else if (!WIFSIGNALED(status) || !WCOREDUMP(status)) { + printf("Child didn't dump core\n"); + return TEST_FAIL; + } + + /* Construct array of core file names to try. */ + + filename[0] = filenames = malloc(PATH_MAX); + if (!filenames) { + perror("Error allocating memory"); + return TEST_FAIL; + } + + ret = snprintf(filename[0], PATH_MAX, "core-pkey.%d", pid); + if (ret < 0 || ret >= PATH_MAX) { + ret = TEST_FAIL; + goto out; + } + + filename[1] = filename[0] + ret + 1; + ret = snprintf(filename[1], PATH_MAX - ret - 1, "core.%d", pid); + if (ret < 0 || ret >= PATH_MAX - ret - 1) { + ret = TEST_FAIL; + goto out; + } + filename[2] = "core"; + + for (i = 0; i < 3; i++) { + core_size = try_core_file(filename[i], info, pid); + if (core_size != TEST_FAIL) + break; + } + + if (i == 3) { + printf("Couldn't find core file\n"); + ret = TEST_FAIL; + goto out; + } + + fd = open(filename[i], O_RDONLY); + if (fd == -1) { + perror("Error opening core file"); + ret = TEST_FAIL; + goto out; + } + + core = mmap(NULL, core_size, PROT_READ, MAP_PRIVATE, fd, 0); + if (core == (void *) -1) { + perror("Error mmaping core file"); + ret = TEST_FAIL; + goto out; + } + + ret = check_core_file(info, core, core_size); + + munmap(core, core_size); + close(fd); + unlink(filename[i]); + + out: + free(filenames); + + return ret; +} + +static int write_core_pattern(const char *core_pattern) +{ + size_t len = strlen(core_pattern), ret; + FILE *f; + + f = fopen(core_pattern_file, "w"); + if (!f) { + perror("Error writing to core_pattern file"); + return TEST_FAIL; + } + + ret = fwrite(core_pattern, 1, len, f); + fclose(f); + if (ret != len) { + perror("Error writing to core_pattern file"); + return TEST_FAIL; + } + + return TEST_PASS; +} + +static int setup_core_pattern(char **core_pattern_, bool *changed_) +{ + FILE *f; + char *core_pattern; + int ret; + + core_pattern = malloc(PATH_MAX); + if (!core_pattern) { + perror("Error allocating memory"); + return TEST_FAIL; + } + + f = fopen(core_pattern_file, "r"); + if (!f) { + perror("Error opening core_pattern file"); + ret = TEST_FAIL; + goto out; + } + + ret = fread(core_pattern, 1, PATH_MAX, f); + fclose(f); + if (!ret) { + perror("Error reading core_pattern file"); + ret = TEST_FAIL; + goto out; + } + + /* Check whether we can predict the name of the core file. */ + if (!strcmp(core_pattern, "core") || !strcmp(core_pattern, "core.%p")) + *changed_ = false; + else { + ret = write_core_pattern("core-pkey.%p"); + if (ret) + goto out; + + *changed_ = true; + } + + *core_pattern_ = core_pattern; + ret = TEST_PASS; + + out: + if (ret) + free(core_pattern); + + return ret; +} + +static int core_pkey(void) +{ + char *core_pattern; + bool changed_core_pattern; + struct shared_info *info; + int shm_id; + int ret; + pid_t pid; + + ret = setup_core_pattern(&core_pattern, &changed_core_pattern); + if (ret) + return ret; + + shm_id = shmget(IPC_PRIVATE, sizeof(*info), 0777 | IPC_CREAT); + info = shmat(shm_id, NULL, 0); + + ret = init_child_sync(&info->child_sync); + if (ret) + return ret; + + pid = fork(); + if (pid < 0) { + perror("fork() failed"); + ret = TEST_FAIL; + } else if (pid == 0) + ret = child(info); + else + ret = parent(info, pid); + + shmdt(info); + + if (pid) { + destroy_child_sync(&info->child_sync); + shmctl(shm_id, IPC_RMID, NULL); + + if (changed_core_pattern) + write_core_pattern(core_pattern); + } + + free(core_pattern); + + return ret; +} + +int main(int argc, char *argv[]) +{ + return test_harness(core_pkey, "core_pkey"); +} diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-hwbreak.c b/tools/testing/selftests/powerpc/ptrace/ptrace-hwbreak.c new file mode 100644 index 000000000000..3066d310f32b --- /dev/null +++ b/tools/testing/selftests/powerpc/ptrace/ptrace-hwbreak.c @@ -0,0 +1,342 @@ +// SPDX-License-Identifier: GPL-2.0+ + +/* + * Ptrace test for hw breakpoints + * + * Based on tools/testing/selftests/breakpoints/breakpoint_test.c + * + * This test forks and the parent then traces the child doing various + * types of ptrace enabled breakpoints + * + * Copyright (C) 2018 Michael Neuling, IBM Corporation. + */ + +#include <sys/ptrace.h> +#include <unistd.h> +#include <stddef.h> +#include <sys/user.h> +#include <stdio.h> +#include <stdlib.h> +#include <signal.h> +#include <sys/types.h> +#include <sys/wait.h> +#include "ptrace.h" + +/* Breakpoint access modes */ +enum { + BP_X = 1, + BP_RW = 2, + BP_W = 4, +}; + +static pid_t child_pid; +static struct ppc_debug_info dbginfo; + +static void get_dbginfo(void) +{ + int ret; + + ret = ptrace(PPC_PTRACE_GETHWDBGINFO, child_pid, NULL, &dbginfo); + if (ret) { + perror("Can't get breakpoint info\n"); + exit(-1); + } +} + +static bool hwbreak_present(void) +{ + return (dbginfo.num_data_bps != 0); +} + +static bool dawr_present(void) +{ + return !!(dbginfo.features & PPC_DEBUG_FEATURE_DATA_BP_DAWR); +} + +static void set_breakpoint_addr(void *addr) +{ + int ret; + + ret = ptrace(PTRACE_SET_DEBUGREG, child_pid, 0, addr); + if (ret) { + perror("Can't set breakpoint addr\n"); + exit(-1); + } +} + +static int set_hwbreakpoint_addr(void *addr, int range) +{ + int ret; + + struct ppc_hw_breakpoint info; + + info.version = 1; + info.trigger_type = PPC_BREAKPOINT_TRIGGER_RW; + info.addr_mode = PPC_BREAKPOINT_MODE_EXACT; + if (range > 0) + info.addr_mode = PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE; + info.condition_mode = PPC_BREAKPOINT_CONDITION_NONE; + info.addr = (__u64)addr; + info.addr2 = (__u64)addr + range; + info.condition_value = 0; + + ret = ptrace(PPC_PTRACE_SETHWDEBUG, child_pid, 0, &info); + if (ret < 0) { + perror("Can't set breakpoint\n"); + exit(-1); + } + return ret; +} + +static int del_hwbreakpoint_addr(int watchpoint_handle) +{ + int ret; + + ret = ptrace(PPC_PTRACE_DELHWDEBUG, child_pid, 0, watchpoint_handle); + if (ret < 0) { + perror("Can't delete hw breakpoint\n"); + exit(-1); + } + return ret; +} + +#define DAWR_LENGTH_MAX 512 + +/* Dummy variables to test read/write accesses */ +static unsigned long long + dummy_array[DAWR_LENGTH_MAX / sizeof(unsigned long long)] + __attribute__((aligned(512))); +static unsigned long long *dummy_var = dummy_array; + +static void write_var(int len) +{ + long long *plval; + char *pcval; + short *psval; + int *pival; + + switch (len) { + case 1: + pcval = (char *)dummy_var; + *pcval = 0xff; + break; + case 2: + psval = (short *)dummy_var; + *psval = 0xffff; + break; + case 4: + pival = (int *)dummy_var; + *pival = 0xffffffff; + break; + case 8: + plval = (long long *)dummy_var; + *plval = 0xffffffffffffffffLL; + break; + } +} + +static void read_var(int len) +{ + char cval __attribute__((unused)); + short sval __attribute__((unused)); + int ival __attribute__((unused)); + long long lval __attribute__((unused)); + + switch (len) { + case 1: + cval = *(char *)dummy_var; + break; + case 2: + sval = *(short *)dummy_var; + break; + case 4: + ival = *(int *)dummy_var; + break; + case 8: + lval = *(long long *)dummy_var; + break; + } +} + +/* + * Do the r/w accesses to trigger the breakpoints. And run + * the usual traps. + */ +static void trigger_tests(void) +{ + int len, ret; + + ret = ptrace(PTRACE_TRACEME, 0, NULL, 0); + if (ret) { + perror("Can't be traced?\n"); + return; + } + + /* Wake up father so that it sets up the first test */ + kill(getpid(), SIGUSR1); + + /* Test write watchpoints */ + for (len = 1; len <= sizeof(long); len <<= 1) + write_var(len); + + /* Test read/write watchpoints (on read accesses) */ + for (len = 1; len <= sizeof(long); len <<= 1) + read_var(len); + + /* Test when breakpoint is unset */ + + /* Test write watchpoints */ + for (len = 1; len <= sizeof(long); len <<= 1) + write_var(len); + + /* Test read/write watchpoints (on read accesses) */ + for (len = 1; len <= sizeof(long); len <<= 1) + read_var(len); +} + +static void check_success(const char *msg) +{ + const char *msg2; + int status; + + /* Wait for the child to SIGTRAP */ + wait(&status); + + msg2 = "Failed"; + + if (WIFSTOPPED(status) && WSTOPSIG(status) == SIGTRAP) { + msg2 = "Child process hit the breakpoint"; + } + + printf("%s Result: [%s]\n", msg, msg2); +} + +static void launch_watchpoints(char *buf, int mode, int len, + struct ppc_debug_info *dbginfo, bool dawr) +{ + const char *mode_str; + unsigned long data = (unsigned long)(dummy_var); + int wh, range; + + data &= ~0x7UL; + + if (mode == BP_W) { + data |= (1UL << 1); + mode_str = "write"; + } else { + data |= (1UL << 0); + data |= (1UL << 1); + mode_str = "read"; + } + + /* Set DABR_TRANSLATION bit */ + data |= (1UL << 2); + + /* use PTRACE_SET_DEBUGREG breakpoints */ + set_breakpoint_addr((void *)data); + ptrace(PTRACE_CONT, child_pid, NULL, 0); + sprintf(buf, "Test %s watchpoint with len: %d ", mode_str, len); + check_success(buf); + /* Unregister hw brkpoint */ + set_breakpoint_addr(NULL); + + data = (data & ~7); /* remove dabr control bits */ + + /* use PPC_PTRACE_SETHWDEBUG breakpoint */ + if (!(dbginfo->features & PPC_DEBUG_FEATURE_DATA_BP_RANGE)) + return; /* not supported */ + wh = set_hwbreakpoint_addr((void *)data, 0); + ptrace(PTRACE_CONT, child_pid, NULL, 0); + sprintf(buf, "Test %s watchpoint with len: %d ", mode_str, len); + check_success(buf); + /* Unregister hw brkpoint */ + del_hwbreakpoint_addr(wh); + + /* try a wider range */ + range = 8; + if (dawr) + range = 512 - ((int)data & (DAWR_LENGTH_MAX - 1)); + wh = set_hwbreakpoint_addr((void *)data, range); + ptrace(PTRACE_CONT, child_pid, NULL, 0); + sprintf(buf, "Test %s watchpoint with len: %d ", mode_str, len); + check_success(buf); + /* Unregister hw brkpoint */ + del_hwbreakpoint_addr(wh); +} + +/* Set the breakpoints and check the child successfully trigger them */ +static int launch_tests(bool dawr) +{ + char buf[1024]; + int len, i, status; + + struct ppc_debug_info dbginfo; + + i = ptrace(PPC_PTRACE_GETHWDBGINFO, child_pid, NULL, &dbginfo); + if (i) { + perror("Can't set breakpoint info\n"); + exit(-1); + } + if (!(dbginfo.features & PPC_DEBUG_FEATURE_DATA_BP_RANGE)) + printf("WARNING: Kernel doesn't support PPC_PTRACE_SETHWDEBUG\n"); + + /* Write watchpoint */ + for (len = 1; len <= sizeof(long); len <<= 1) + launch_watchpoints(buf, BP_W, len, &dbginfo, dawr); + + /* Read-Write watchpoint */ + for (len = 1; len <= sizeof(long); len <<= 1) + launch_watchpoints(buf, BP_RW, len, &dbginfo, dawr); + + ptrace(PTRACE_CONT, child_pid, NULL, 0); + + /* + * Now we have unregistered the breakpoint, access by child + * should not cause SIGTRAP. + */ + + wait(&status); + + if (WIFSTOPPED(status) && WSTOPSIG(status) == SIGTRAP) { + printf("FAIL: Child process hit the breakpoint, which is not expected\n"); + ptrace(PTRACE_CONT, child_pid, NULL, 0); + return TEST_FAIL; + } + + if (WIFEXITED(status)) + printf("Child exited normally\n"); + + return TEST_PASS; +} + +static int ptrace_hwbreak(void) +{ + pid_t pid; + int ret; + bool dawr; + + pid = fork(); + if (!pid) { + trigger_tests(); + return 0; + } + + wait(NULL); + + child_pid = pid; + + get_dbginfo(); + SKIP_IF(!hwbreak_present()); + dawr = dawr_present(); + + ret = launch_tests(dawr); + + wait(NULL); + + return ret; +} + +int main(int argc, char **argv, char **envp) +{ + return test_harness(ptrace_hwbreak, "ptrace-hwbreak"); +} diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c b/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c new file mode 100644 index 000000000000..5cf631f792cc --- /dev/null +++ b/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c @@ -0,0 +1,327 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Ptrace test for Memory Protection Key registers + * + * Copyright (C) 2015 Anshuman Khandual, IBM Corporation. + * Copyright (C) 2018 IBM Corporation. + */ +#include "ptrace.h" +#include "child.h" + +#ifndef __NR_pkey_alloc +#define __NR_pkey_alloc 384 +#endif + +#ifndef __NR_pkey_free +#define __NR_pkey_free 385 +#endif + +#ifndef NT_PPC_PKEY +#define NT_PPC_PKEY 0x110 +#endif + +#ifndef PKEY_DISABLE_EXECUTE +#define PKEY_DISABLE_EXECUTE 0x4 +#endif + +#define AMR_BITS_PER_PKEY 2 +#define PKEY_REG_BITS (sizeof(u64) * 8) +#define pkeyshift(pkey) (PKEY_REG_BITS - ((pkey + 1) * AMR_BITS_PER_PKEY)) + +static const char user_read[] = "[User Read (Running)]"; +static const char user_write[] = "[User Write (Running)]"; +static const char ptrace_read_running[] = "[Ptrace Read (Running)]"; +static const char ptrace_write_running[] = "[Ptrace Write (Running)]"; + +/* Information shared between the parent and the child. */ +struct shared_info { + struct child_sync child_sync; + + /* AMR value the parent expects to read from the child. */ + unsigned long amr1; + + /* AMR value the parent is expected to write to the child. */ + unsigned long amr2; + + /* AMR value that ptrace should refuse to write to the child. */ + unsigned long amr3; + + /* IAMR value the parent expects to read from the child. */ + unsigned long expected_iamr; + + /* UAMOR value the parent expects to read from the child. */ + unsigned long expected_uamor; + + /* + * IAMR and UAMOR values that ptrace should refuse to write to the child + * (even though they're valid ones) because userspace doesn't have + * access to those registers. + */ + unsigned long new_iamr; + unsigned long new_uamor; +}; + +static int sys_pkey_alloc(unsigned long flags, unsigned long init_access_rights) +{ + return syscall(__NR_pkey_alloc, flags, init_access_rights); +} + +static int sys_pkey_free(int pkey) +{ + return syscall(__NR_pkey_free, pkey); +} + +static int child(struct shared_info *info) +{ + unsigned long reg; + bool disable_execute = true; + int pkey1, pkey2, pkey3; + int ret; + + /* Wait until parent fills out the initial register values. */ + ret = wait_parent(&info->child_sync); + if (ret) + return ret; + + /* Get some pkeys so that we can change their bits in the AMR. */ + pkey1 = sys_pkey_alloc(0, PKEY_DISABLE_EXECUTE); + if (pkey1 < 0) { + pkey1 = sys_pkey_alloc(0, 0); + CHILD_FAIL_IF(pkey1 < 0, &info->child_sync); + + disable_execute = false; + } + + pkey2 = sys_pkey_alloc(0, 0); + CHILD_FAIL_IF(pkey2 < 0, &info->child_sync); + + pkey3 = sys_pkey_alloc(0, 0); + CHILD_FAIL_IF(pkey3 < 0, &info->child_sync); + + info->amr1 |= 3ul << pkeyshift(pkey1); + info->amr2 |= 3ul << pkeyshift(pkey2); + info->amr3 |= info->amr2 | 3ul << pkeyshift(pkey3); + + if (disable_execute) + info->expected_iamr |= 1ul << pkeyshift(pkey1); + + info->expected_uamor |= 3ul << pkeyshift(pkey1) | + 3ul << pkeyshift(pkey2); + info->new_iamr |= 1ul << pkeyshift(pkey1) | 1ul << pkeyshift(pkey2); + info->new_uamor |= 3ul << pkeyshift(pkey1); + + /* + * We won't use pkey3. We just want a plausible but invalid key to test + * whether ptrace will let us write to AMR bits we are not supposed to. + * + * This also tests whether the kernel restores the UAMOR permissions + * after a key is freed. + */ + sys_pkey_free(pkey3); + + printf("%-30s AMR: %016lx pkey1: %d pkey2: %d pkey3: %d\n", + user_write, info->amr1, pkey1, pkey2, pkey3); + + mtspr(SPRN_AMR, info->amr1); + + /* Wait for parent to read our AMR value and write a new one. */ + ret = prod_parent(&info->child_sync); + CHILD_FAIL_IF(ret, &info->child_sync); + + ret = wait_parent(&info->child_sync); + if (ret) + return ret; + + reg = mfspr(SPRN_AMR); + + printf("%-30s AMR: %016lx\n", user_read, reg); + + CHILD_FAIL_IF(reg != info->amr2, &info->child_sync); + + /* + * Wait for parent to try to write an invalid AMR value. + */ + ret = prod_parent(&info->child_sync); + CHILD_FAIL_IF(ret, &info->child_sync); + + ret = wait_parent(&info->child_sync); + if (ret) + return ret; + + reg = mfspr(SPRN_AMR); + + printf("%-30s AMR: %016lx\n", user_read, reg); + + CHILD_FAIL_IF(reg != info->amr2, &info->child_sync); + + /* + * Wait for parent to try to write an IAMR and a UAMOR value. We can't + * verify them, but we can verify that the AMR didn't change. + */ + ret = prod_parent(&info->child_sync); + CHILD_FAIL_IF(ret, &info->child_sync); + + ret = wait_parent(&info->child_sync); + if (ret) + return ret; + + reg = mfspr(SPRN_AMR); + + printf("%-30s AMR: %016lx\n", user_read, reg); + + CHILD_FAIL_IF(reg != info->amr2, &info->child_sync); + + /* Now let parent now that we are finished. */ + + ret = prod_parent(&info->child_sync); + CHILD_FAIL_IF(ret, &info->child_sync); + + return TEST_PASS; +} + +static int parent(struct shared_info *info, pid_t pid) +{ + unsigned long regs[3]; + int ret, status; + + /* + * Get the initial values for AMR, IAMR and UAMOR and communicate them + * to the child. + */ + ret = ptrace_read_regs(pid, NT_PPC_PKEY, regs, 3); + PARENT_SKIP_IF_UNSUPPORTED(ret, &info->child_sync); + PARENT_FAIL_IF(ret, &info->child_sync); + + info->amr1 = info->amr2 = info->amr3 = regs[0]; + info->expected_iamr = info->new_iamr = regs[1]; + info->expected_uamor = info->new_uamor = regs[2]; + + /* Wake up child so that it can set itself up. */ + ret = prod_child(&info->child_sync); + PARENT_FAIL_IF(ret, &info->child_sync); + + ret = wait_child(&info->child_sync); + if (ret) + return ret; + + /* Verify that we can read the pkey registers from the child. */ + ret = ptrace_read_regs(pid, NT_PPC_PKEY, regs, 3); + PARENT_FAIL_IF(ret, &info->child_sync); + + printf("%-30s AMR: %016lx IAMR: %016lx UAMOR: %016lx\n", + ptrace_read_running, regs[0], regs[1], regs[2]); + + PARENT_FAIL_IF(regs[0] != info->amr1, &info->child_sync); + PARENT_FAIL_IF(regs[1] != info->expected_iamr, &info->child_sync); + PARENT_FAIL_IF(regs[2] != info->expected_uamor, &info->child_sync); + + /* Write valid AMR value in child. */ + ret = ptrace_write_regs(pid, NT_PPC_PKEY, &info->amr2, 1); + PARENT_FAIL_IF(ret, &info->child_sync); + + printf("%-30s AMR: %016lx\n", ptrace_write_running, info->amr2); + + /* Wake up child so that it can verify it changed. */ + ret = prod_child(&info->child_sync); + PARENT_FAIL_IF(ret, &info->child_sync); + + ret = wait_child(&info->child_sync); + if (ret) + return ret; + + /* Write invalid AMR value in child. */ + ret = ptrace_write_regs(pid, NT_PPC_PKEY, &info->amr3, 1); + PARENT_FAIL_IF(ret, &info->child_sync); + + printf("%-30s AMR: %016lx\n", ptrace_write_running, info->amr3); + + /* Wake up child so that it can verify it didn't change. */ + ret = prod_child(&info->child_sync); + PARENT_FAIL_IF(ret, &info->child_sync); + + ret = wait_child(&info->child_sync); + if (ret) + return ret; + + /* Try to write to IAMR. */ + regs[0] = info->amr1; + regs[1] = info->new_iamr; + ret = ptrace_write_regs(pid, NT_PPC_PKEY, regs, 2); + PARENT_FAIL_IF(!ret, &info->child_sync); + + printf("%-30s AMR: %016lx IAMR: %016lx\n", + ptrace_write_running, regs[0], regs[1]); + + /* Try to write to IAMR and UAMOR. */ + regs[2] = info->new_uamor; + ret = ptrace_write_regs(pid, NT_PPC_PKEY, regs, 3); + PARENT_FAIL_IF(!ret, &info->child_sync); + + printf("%-30s AMR: %016lx IAMR: %016lx UAMOR: %016lx\n", + ptrace_write_running, regs[0], regs[1], regs[2]); + + /* Verify that all registers still have their expected values. */ + ret = ptrace_read_regs(pid, NT_PPC_PKEY, regs, 3); + PARENT_FAIL_IF(ret, &info->child_sync); + + printf("%-30s AMR: %016lx IAMR: %016lx UAMOR: %016lx\n", + ptrace_read_running, regs[0], regs[1], regs[2]); + + PARENT_FAIL_IF(regs[0] != info->amr2, &info->child_sync); + PARENT_FAIL_IF(regs[1] != info->expected_iamr, &info->child_sync); + PARENT_FAIL_IF(regs[2] != info->expected_uamor, &info->child_sync); + + /* Wake up child so that it can verify AMR didn't change and wrap up. */ + ret = prod_child(&info->child_sync); + PARENT_FAIL_IF(ret, &info->child_sync); + + ret = wait(&status); + if (ret != pid) { + printf("Child's exit status not captured\n"); + ret = TEST_PASS; + } else if (!WIFEXITED(status)) { + printf("Child exited abnormally\n"); + ret = TEST_FAIL; + } else + ret = WEXITSTATUS(status) ? TEST_FAIL : TEST_PASS; + + return ret; +} + +static int ptrace_pkey(void) +{ + struct shared_info *info; + int shm_id; + int ret; + pid_t pid; + + shm_id = shmget(IPC_PRIVATE, sizeof(*info), 0777 | IPC_CREAT); + info = shmat(shm_id, NULL, 0); + + ret = init_child_sync(&info->child_sync); + if (ret) + return ret; + + pid = fork(); + if (pid < 0) { + perror("fork() failed"); + ret = TEST_FAIL; + } else if (pid == 0) + ret = child(info); + else + ret = parent(info, pid); + + shmdt(info); + + if (pid) { + destroy_child_sync(&info->child_sync); + shmctl(shm_id, IPC_RMID, NULL); + } + + return ret; +} + +int main(int argc, char *argv[]) +{ + return test_harness(ptrace_pkey, "ptrace_pkey"); +} diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace.h b/tools/testing/selftests/powerpc/ptrace/ptrace.h index 19fb825270a1..34201cfa8335 100644 --- a/tools/testing/selftests/powerpc/ptrace/ptrace.h +++ b/tools/testing/selftests/powerpc/ptrace/ptrace.h @@ -102,6 +102,44 @@ int cont_trace(pid_t child) return TEST_PASS; } +int ptrace_read_regs(pid_t child, unsigned long type, unsigned long regs[], + int n) +{ + struct iovec iov; + long ret; + + FAIL_IF(start_trace(child)); + + iov.iov_base = regs; + iov.iov_len = n * sizeof(unsigned long); + + ret = ptrace(PTRACE_GETREGSET, child, type, &iov); + if (ret) + return ret; + + FAIL_IF(stop_trace(child)); + + return TEST_PASS; +} + +long ptrace_write_regs(pid_t child, unsigned long type, unsigned long regs[], + int n) +{ + struct iovec iov; + long ret; + + FAIL_IF(start_trace(child)); + + iov.iov_base = regs; + iov.iov_len = n * sizeof(unsigned long); + + ret = ptrace(PTRACE_SETREGSET, child, type, &iov); + + FAIL_IF(stop_trace(child)); + + return ret; +} + /* TAR, PPR, DSCR */ int show_tar_registers(pid_t child, unsigned long *out) { diff --git a/tools/testing/selftests/powerpc/tm/.gitignore b/tools/testing/selftests/powerpc/tm/.gitignore index bb90d4b79524..c3ee8393dae8 100644 --- a/tools/testing/selftests/powerpc/tm/.gitignore +++ b/tools/testing/selftests/powerpc/tm/.gitignore @@ -14,3 +14,4 @@ tm-signal-context-chk-vsx tm-vmx-unavail tm-unavailable tm-trap +tm-sigreturn |